Papers › PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

2 Dec 2016CVPR 2017 7arXiv:1612.00593archive 2025-07-28

Charles R. Qi, Hao Su, Kaichun Mo, Leonidas J. Guibas

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds and well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 164 code samples harvested from 44 repositories linked to this paper: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified. Where Syntology's instrument failed: 14 where our contract draft was wrong; 15 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 164 samples from 44 repositories, 103 ran (74 with no instrument failure; 29 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

110 repositories listed; official and paper-mentioned ones first.

2023-MindSpore-1/ms-code-35 mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
AI-Guru/pointcloud_experiments mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
AlfredoZermini/PointNet mentioned on GitHubSyntology: not harvested report
AndreiMoraru123/PointNet mentioned on GitHubpytorchSyntology: not harvested report
BPMJG/annotated_pointnet mentioned on GitHubtfSyntology: not harvested report
CheesyB/cpointnet mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
Dir-b/PointNet mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
DylanWusee/pointconv_pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointConv: Deep Convolutional Networks on 3D Point Clouds (arXiv:1811.07246; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
ECE685-FinalProject/3D-object-recognition mentioned on GitHubpytorchSyntology: 9 samples, 7 ran (5 instrument-failed) · 2 unverified report
Fragjacker/Pointcloud-grad-CAM mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization (arXiv:1610.02391; that paper's own run record: 90 ran (of which 32 constructed an object rather than computing a result; 62 with no instrument failure: 6 honoured, 4 violated, 52 with no contract checked; 28 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
GOD-GOD-Autonomous-Vehicle/self-pointnet mentioned on GitHubpytorchMITSyntology: not harvested report
Harut0726/my-pointnet-tensorflow mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
Jagyan/ghost_radarpoint_detection mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
Javed002/Object_detection_PointNet mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
KaidongLi/tf-3d-alpha mentioned on GitHubtfSyntology: not harvested report
KhusDM/PointNetTree mentioned on GitHubtfSyntology: not harvested report
KiranAkadas/My_Pointnet_v2 mentioned on GitHubtfSyntology: 12 samples, 4 ran (4 instrument-failed) · 8 unverified report
LONG-9621/Extract_Point_3D mentioned on GitHubtfSyntology: not harvested report
LONG-9621/PointNet mentioned on GitHubtfSyntology: not harvested report
LebronGG/PointNet mentioned on GitHubtfSyntology: not harvested report
Lw510107/pointnet-2018.6.27- mentioned on GitHubtfSyntology: not harvested report
ModelBunker/PointNet-TensorFlow mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
Moon-Xuezha/PointNet mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
PaParaZz1/PointNet mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
Phimos/Paddle-PointNet mentioned on GitHubpaddleSyntology: not harvested report
SBPL-Cruz/perch_pose_sampler mentioned on GitHubpytorchMITSyntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
SY-Xuan/pointnet_paddle mentioned on GitHubpaddleSyntology: not harvested report
ShadowShadowWong/update-pointnet-work mentioned on GitHubpytorchMITSyntology: not harvested report
SonuDileep/3-D-Object-Detection-using-PointNet mentioned on GitHubtfSyntology: 12 samples, 6 ran (6 instrument-failed) · 6 unverified report
THHHomas/mls mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointConv: Deep Convolutional Networks on 3D Point Clouds (arXiv:1811.07246; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
Taeuk-Jang/pointcompletion mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
VaanHUANG/CSCI5210HW1 mentioned on GitHubtfSyntology: not harvested report
WangYueFt/dgcnn mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
YanWei123/PointNet-encoder-and-FoldingNet-decoder-add-quantization-change-latent-code-size-from-512-to-1024 mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
YanWei123/Pointnet_encoder_Foldingnet_decoder_quantization mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
YanWei123/Pytorch-implementation-of-FoldingNet-encoder-and-decoder-with-graph-pooling-covariance-add-quanti mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
Yang2446/pointnet mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PCPNET: Learning Local Shape Properties from Raw Point Clouds (arXiv:1710.04954; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
YiruS/pointnet_adversarial mentioned on GitHubtfSyntology: not harvested report
Young98CN/pointconv_pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
Yuto0107/pointnet mentioned on GitHubpytorchSyntology: not harvested report
ZhihaoZhu/PointNet-Implementation-Tensorflow mentioned on GitHubtfSyntology: not harvested report
abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds mentioned on GitHubtfSyntology: 12 samples, 0 ran · 12 unverified report
ahmed-anas/thesis-pointnet mentioned on GitHubtfSyntology: not harvested report
ajertec/PointNetKeras mentioned on GitHubtfSyntology: 4 samples, 0 ran · 4 unverified report
ajhamdi/AdvPC mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds (arXiv:1912.00461; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
ali-stanford/pointnetcfd mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
alpemek/ais3d mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Frustum PointNets for 3D Object Detection from RGB-D Data (arXiv:1711.08488; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
amyllykoski/CycleGAN mentioned on GitHubpytorchSyntology: not harvested report
aviros/pointnet_totations mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
aviros/roatationPointnet mentioned on GitHubtfSyntology: not harvested report
brendanmallery9/entropic-barycenters mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
bt77/pointnet mentioned on GitHubtfSyntology: not harvested report
charlesq34/pointnet mentioned on GitHubtfSyntology: not harvested report
coconutzs/PointNet_zs mentioned on GitHubtfSyntology: not harvested report
donshen/pointnet.phasedetection mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
dwtstore/sfm1 mentioned on GitHubtfSyntology: not harvested report
eth212/Qmind_ModelNet10_PointNet mentioned on GitHubtfSyntology: not harvested report
freddieee/pn_6d_single mentioned on GitHubpytorchMITSyntology: not harvested report
ftdlyc/pointnet_pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
fxia22/pointnet.pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
hnVfly/pointnet.mxnet mentioned on GitHubtfMITSyntology: not harvested report
hnmspirit/pointnet1 mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
hz-ants/pointnet.pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
imanlab/deep_movement_primitives mentioned on GitHubtfSyntology: not harvested report
jtpils/treegan mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
lingzhang1/pointnet_pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
lingzhang1/pointnet_tensorflow mentioned on GitHubtfSyntology: 4 samples, 0 ran · 4 unverified report
liuch37/pointnet mentioned on GitHubpytorchMITSyntology: not harvested report
m-117/PointNet-ein-Implementationsbeispiel-mit-Jupyter-Notebooks mentioned on GitHubtfMITSyntology: not harvested report
maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Graph-CNN for 3D Point Cloud Classification (arXiv:1812.01711; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
mengxingshifen1218/pointnet.pytorch mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
merazlab/3D_Deep_Learning_Link mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
minhncedutw/pointnet1_keras mentioned on GitHubtfSyntology: 5 samples, 3 ran (3 instrument-failed) · 2 unverified report
nddoshi/pointnet mentioned on GitHubpytorchSyntology: not harvested report
nikitakaraevv/pointnet mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
opeco17/pointnet mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
prasadsawant5/PointNet mentioned on GitHubtfSyntology: 4 samples, 0 ran · 4 unverified report
romaintha/pytorch_pointnet mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
saaries/PointNet mentioned on GitHubpytorchMITSyntology: not harvested report
sanantoniochili/PointCloud_KNN mentioned on GitHubtfSyntology: not harvested report
sarthakTUM/roofn3d mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
smfirmin/DeepLearningFinalProject mentioned on GitHubpytorchSyntology: 6 samples, 3 ran (0 instrument-failed) · 3 unverified report
soumik12345/point-cloud-segmentation mentioned on GitHubtfSyntology: 6 samples, 5 ran (4 instrument-failed) · 1 unverified report
timothylimyl/PointNet-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
vinits5/learning3d mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
witignite/Frustum-PointNet mentioned on GitHubtfSyntology: not harvested report
wonderland-dsg/pointnet-grid mentioned on GitHubtfSyntology: not harvested report
wuryantoAji/POINTNET mentioned on GitHubtfSyntology: not harvested report
xurui1217/pointnet.pytorch-master mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
y2kmz/pointnetv2 mentioned on GitHubtfSyntology: 8 samples, 4 ran (4 instrument-failed) · 4 unverified report
yangyucheng000/pointnet mentioned on GitHubmindsporeApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
yanx27/Pointnet mentioned on GitHubtfSyntology: not harvested report
yanxp/PointNet mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
yevgm/deepadv3d mentioned on GitHubpytorchSyntology: not harvested report
ytng001/sensemaking mentioned on GitHubtfSyntology: not harvested report
zgx0534/pointnet_win mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
gitee.com/gai-shaoyan/mind3d Syntology: not harvested report
2023-MindSpore-1/ms-code-7 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code9 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large... (arXiv:2305.05773; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Cmeijiang/PointNet_MS mindsporeSyntology: not harvested report
Mind23-2/MindCode-63 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
debajyotid2/pointnet_pl pytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
princeton-vl/SimpleView pytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
xiuyu0000/vision mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

164 samples harvested: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

14ran · our draft was wrong
15ran; the contract check could not run
74ran
61unverified

Licence: 92 of the 164 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 44 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 29 samples that ran, the graph records a signature this page does not show, each row saying why in its tooltip: for 28, for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments; for 1, an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

AI-Guru/pointcloud_experiments community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
MatMul model_cls.py ran no licence file found · pointer only · 3829b0b4b30416c1 · report fixture: signature inputs:list/1/EagerTensor · returned EagerTensor · level recorded 2026-09-24
create_pointnet model_cls.py unverified no licence file found · pointer only · 3c2bc65ae780dfe3 · report
CheesyB/cpointnet community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
PointNetCls pointnet.py ran MIT (permissive) · 26589a98563a59d0 · report fixture: returned PointNetCls · level recorded 2026-09-22
PointNetfeat pointnet.py ran MIT (permissive) · 62f355b393ae1ca7 · report fixture: returned PointNetfeat · level recorded 2026-09-22
STN3d pointnet.py ran MIT (permissive) · 4626eef340141c25 · report fixture: returned STN3d · level recorded 2026-09-22
Dir-b/PointNet community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
feature_transform_regularizer in 9 papers pointnet/model.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · e996c64ee89d2b50 · report fixture: signature trans:Tensor/3/float · returned Tensor · level recorded 2026-09-24
ECE685-FinalProject/3D-object-recognition community (archive-listed) 9 samples, 7 ran (5 instrument-failed) · 2 unverified
DensityNet model/pointconv.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 101276f7d87be7cb · report fixture: returned DensityNet · level recorded 2026-09-22
WeightNet model/pointconv.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 8c2830b15e8dcd52 · report fixture: returned WeightNet · level recorded 2026-09-22
compute_density model/pointconv.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 99c35218cb2a376b · report fixture: signature xyz:Tensor/3/float, bandwidth:float/0/float · returned Tensor · level recorded 2026-09-22
farthest_point_sample in 64 papers model/pointconv.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · b9f3546dde325b9a · report fixture: signature xyz:Tensor/3/float, npoint:int/0/int · returned Tensor · level recorded 2026-09-22
knn_point in 23 papers
census: 4 implementations from 5 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
model/pointconv.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 07c115b84ba5c7c6 · report fixture: signature nsample:int/0/int, xyz:Tensor/3/float, new_xyz:Tensor/3/float · returned Tensor · level recorded 2026-09-22
sample_and_group in 10 papers model/pointconv.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · db1c207b74c5a727 · report fixture: signature npoint:int/0/int, nsample:int/0/int, xyz:Tensor/3/float, points:Tensor/3/float, density_scale:Tensor/3/float · returned tuple · level recorded 2026-09-22
sample_and_group_all in 26 papers model/pointconv.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 5df806877e088158 · report fixture: signature xyz:Tensor/3/float, points:Tensor/3/float, density_scale:Tensor/2/float · returned tuple · level recorded 2026-09-22
PointConvDensityClsSsg model/pointconv.py unverified no licence file found · pointer only · 78fb790141929709 · report
PointConvDensitySetAbstraction model/pointconv.py unverified no licence file found · pointer only · a55dec597b21030d · report
Harut0726/my-pointnet-tensorflow community (archive-listed) 1 sample, 0 ran · 1 unverified
get_model in 368 papers models/pointnet_cls.py unverified licence not identified · pointer only · c6f443774c59dbf0 · report
Jagyan/ghost_radarpoint_detection community (archive-listed) 1 sample, 0 ran · 1 unverified
PointNetCls pointnet/model.py unverified MIT (permissive) · 1931553e6c254e09 · report
Javed002/Object_detection_PointNet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
read_off in 6 papers utils.py ran Apache-2.0 (permissive) · 963cff4d425b22eb · report fixture: signature file:StringIO/0/? · returned tuple · level recorded 2026-09-26
KiranAkadas/My_Pointnet_v2 community (archive-listed) 12 samples, 4 ran (4 instrument-failed) · 8 unverified
_variable_on_cpu models/pointnet_cls.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 26d314e83af41fab · report fixture: signature name:str/0/str, shape:list/1/int, initializer:callable/0/?, use_fp16:bool/0/bool · returned ResourceVariable · level recorded 2026-09-22
_variable_with_weight_decay models/pointnet_cls.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 87f93d0c7129ee4e · report fixture: returned ResourceVariable · level recorded 2026-09-22
dropout in 34 papers models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · b9cc54403e6c3be8 · report fixture: returned EagerTensor · level recorded 2026-09-22
max_pool2d models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · 367777b5febe9b58 · report fixture: signature inputs:SymbolicTensor/4/float, kernel_size:list/1/int, scope:str/0/str, stride:list/1/int, padding:str/0/str · returned EagerTensor · level recorded 2026-09-22
batch_norm_for_conv2d models/pointnet_cls.py unverified licence not identified · pointer only · 762f096e29d11bf9 · report
batch_norm_for_fc models/pointnet_cls.py unverified licence not identified · pointer only · e25a0bc56534a31f · report
batch_norm_template models/pointnet_cls.py unverified licence not identified · pointer only · 88e171f204372a23 · report
conv2d in 119 papers models/pointnet_cls.py unverified licence not identified · pointer only · 0ed2449abae99e7d · report
feature_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · 2862f30a5a09b5f0 · report
fully_connected in 9 papers models/pointnet_cls.py unverified licence not identified · pointer only · 85a6137807ce8849 · report
get_model in 368 papers models/pointnet_cls.py unverified licence not identified · pointer only · 1a2be9b9d77bfa7e · report
input_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · 096e87fb2226873a · report
ModelBunker/PointNet-TensorFlow community (archive-listed) 1 sample, 0 ran · 1 unverified
get_model in 368 papers models/pointnet_cls.py unverified licence not identified · pointer only · ebf79aab4c147450 · report
PaParaZz1/PointNet community (archive-listed) 6 samples, 5 ran (2 instrument-failed) · 1 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
network.py ran · our draft was wrong MIT (permissive) · 0500691c048885c9 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, init_type:str/0/str, activation:callable/0/?, use_batchnorm:bool/0/bool · returned list · level recorded 2026-09-22
ConvBlockSequential network.py ran · our draft was wrong MIT (permissive) · d35a1145885d3159 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, init_type:str/0/str, activation:callable/0/?, use_batchnorm:bool/0/bool · returned Sequential · level recorded 2026-09-22
FeatureTransform network.py ran · metamorphic tier: invariant MIT (permissive) · e7a88d785b2894ba · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
InputTransform network.py ran fingerprinted MIT (permissive) · d4c6fdd6cac8cdfa · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
PointNetSeg network.py ran fingerprinted MIT (permissive) · 8727e973f8a99293 · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-24
WeightInitialize network.py unverified MIT (permissive) · 064af42f9ae964af · report
SBPL-Cruz/perch_pose_sampler community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
conv3x3 in 1,376 papers pointnet/extractors.py ran MIT (permissive) here; the stored copy is pointer only · 48f5a5ec1d5dd2ef · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-24
get_bbox in 19 papers pointnet/dataset.py ran MIT (permissive) · d9064882510d8ae7 · report fixture: signature label:ndarray/2/int · returned tuple · level recorded 2026-09-26
reflection_matrix in 15 papers utils/transformations.py ran fingerprinted MIT (permissive) · f7f6bfdeee237f86 · report fixture: signature point:ndarray/1/float, normal:ndarray/1/float · returned ndarray · level recorded 2026-09-25
resnet18 in 432 papers pointnet/extractors.py ran MIT (permissive) · 05c290474d8f5351 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
resnet34 in 148 papers pointnet/extractors.py ran MIT (permissive) · 55172193d5361242 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
translation_from_matrix in 15 papers utils/transformations.py ran fingerprinted MIT (permissive) · 77cb383b0cd2a54e · report fixture: signature matrix:ndarray/2/float · returned ndarray · level recorded 2026-09-25
translation_matrix in 15 papers utils/transformations.py ran fingerprinted MIT (permissive) · edeb1406911ce025 · report fixture: signature direction:ndarray/1/float · returned ndarray · level recorded 2026-09-25
SonuDileep/3-D-Object-Detection-using-PointNet community (archive-listed) 12 samples, 6 ran (6 instrument-failed) · 6 unverified
_variable_on_cpu models/pointnet_cls.py ran; the contract check could not run (RAISES) licence not identified · pointer only · fc8746ccaf51b7f9 · report fixture: signature name:str/0/str, shape:list/1/int, initializer:callable/0/?, use_fp16:bool/0/bool · returned RefVariable · level recorded 2026-09-22
batch_norm_for_conv2d models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · 9004a85393cde41f · report fixture: signature inputs:SymbolicTensor/4/float, is_training:RefVariable/0/bool, bn_decay:float/0/float, scope:str/0/str · returned SymbolicTensor · level recorded 2026-09-22
batch_norm_for_fc models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · 2863ce9bf49d2a64 · report fixture: signature inputs:SymbolicTensor/2/float, is_training:SymbolicTensor/0/bool, bn_decay:float/0/float, scope:str/0/str · returned SymbolicTensor · level recorded 2026-09-22
batch_norm_template models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · 1af511204765af4b · report fixture: signature inputs:SymbolicTensor/4/float, is_training:SymbolicTensor/0/bool, scope:str/0/str, moments_dims:list/1/int, bn_decay:float/0/float · returned SymbolicTensor · level recorded 2026-09-22
dropout in 34 papers models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · 3d9def431518fbd7 · report fixture: signature inputs:SymbolicTensor/2/float, is_training:RefVariable/0/bool, scope:str/0/str, keep_prob:float/0/float, noise_shape:list/1/int · returned SymbolicTensor · level recorded 2026-09-22
max_pool2d models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · da8ec247588f65ab · report fixture: signature inputs:SymbolicTensor/4/float, kernel_size:list/1/int, scope:str/0/str, stride:list/1/int, padding:str/0/str · returned SymbolicTensor · level recorded 2026-09-22
_variable_with_weight_decay models/pointnet_cls.py unverified licence not identified · pointer only · 29aec8f56b55e088 · report
conv2d in 119 papers models/pointnet_cls.py unverified licence not identified · pointer only · 374342af0b0ba20f · report
feature_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · 36b2d51234710715 · report
fully_connected in 9 papers models/pointnet_cls.py unverified licence not identified · pointer only · 435b6ba762fa962f · report
get_model in 368 papers models/pointnet_cls.py unverified licence not identified · pointer only · 659d22edcdc360d2 · report
input_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · 47128c57bbc8285e · report
Taeuk-Jang/pointcompletion community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
PointNetfeat pointnet/model.py ran fingerprinted MIT (permissive) · a0a98d1455e2700c · report fixture: returned PointNetfeat · level recorded 2026-09-22
STN3d pointnet/model.py ran fingerprinted MIT (permissive) · 9de2aaf78bbf10fd · report fixture: returned STN3d · level recorded 2026-09-22
STN4d pointnet/model.py ran fingerprinted MIT (permissive) · c51d2646e1f8707c · report fixture: returned STN4d · level recorded 2026-09-22
STNkd pointnet/model.py ran fingerprinted MIT (permissive) · bcbe4bef55f4d2d1 · report fixture: returned STNkd · level recorded 2026-09-22
WangYueFt/dgcnn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PointNet in 5 papers pytorch/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · d49fb29dc696ee6c · report fixture: returned PointNet · level recorded 2026-09-22
YanWei123/PointNet-encoder-and-FoldingNet-decoder-add-quantization-change-latent-code-size-from-512-to-1024 community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
PointNetCls pointnet.py ran fingerprinted MIT (permissive) · 6dcbc51747a8bb73 · report fixture: returned PointNetCls · level recorded 2026-09-22
PointNetfeat pointnet.py ran fingerprinted MIT (permissive) · 5a5a64fad512c4b2 · report fixture: returned PointNetfeat · level recorded 2026-09-22
STN3d pointnet.py ran fingerprinted MIT (permissive) · 00b768e2c62c92bc · report fixture: returned STN3d · level recorded 2026-09-22
YanWei123/Pointnet_encoder_Foldingnet_decoder_quantization community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
ChamferDistance pointnet.py ran fingerprinted MIT (permissive) · 2bb949769eebab26 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-26
GridSamplingLayer pointnet.py ran MIT (permissive) · f0f053f931f94251 · report fixture: signature batch_size:int/0/int, meshgrid:list/1/list · returned ndarray · level recorded 2026-09-26
YanWei123/Pytorch-implementation-of-FoldingNet-encoder-and-decoder-with-graph-pooling-covariance-add-quanti community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
build_graph_core prepare_graph.py ran MIT (permissive) · 3aa740fd1e57b91d · report fixture: signature ith_datai:ndarray/2/float, args:Args/0/? · returned tuple · level recorded 2026-09-26
edges2A prepare_graph.py ran MIT (permissive) · bac594b9f7fe23ed · report fixture: returned csr_matrix · level recorded 2026-09-26
knn_search prepare_graph.py unverified MIT (permissive) · 971853ff05eb788d · report
abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds community (archive-listed) 12 samples, 0 ran · 12 unverified
_variable_on_cpu models/pointnet_cls.py unverified licence not identified · pointer only · 0e8b6b26d8827177 · report
_variable_with_weight_decay models/pointnet_cls.py unverified licence not identified · pointer only · cd31f214652ec580 · report
batch_norm_for_conv2d models/pointnet_cls.py unverified licence not identified · pointer only · e767d7c8946f4c9a · report
batch_norm_for_fc models/pointnet_cls.py unverified licence not identified · pointer only · 5cf119ef55c54349 · report
batch_norm_template models/pointnet_cls.py unverified licence not identified · pointer only · 1e3a7b062fd34628 · report
conv2d in 119 papers models/pointnet_cls.py unverified licence not identified · pointer only · 3471f8d470b6a58d · report
dropout in 34 papers models/pointnet_cls.py unverified licence not identified · pointer only · c59b25c37b041301 · report
feature_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · c208adaa3faf9c5c · report
fully_connected in 9 papers models/pointnet_cls.py unverified licence not identified · pointer only · 5a22ecfcfb8dd56f · report
get_model in 368 papers models/pointnet_cls.py unverified licence not identified · pointer only · 3348d605b8bb0364 · report
input_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · 53ab45fb2b1c27fb · report
max_pool2d models/pointnet_cls.py unverified licence not identified · pointer only · ceb4bc5d5bdb28a9 · report
ajertec/PointNetKeras community (archive-listed) 4 samples, 0 ran · 4 unverified
frobenius_norm models.py unverified no licence file found · pointer only · b326dccf1b38873f · report
orthogonality_reg models.py unverified no licence file found · pointer only · f703b64c37ee8c75 · report
pointnet_cls models.py unverified no licence file found · pointer only · 17058c05afc3f8c5 · report
t_net models.py unverified no licence file found · pointer only · 53fb6fa3c4fbe5f3 · report
ali-stanford/pointnetcfd community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PointNetMLP PyTorchVersion/PointNetCFD.py ran · metamorphic tier: deterministic MIT (permissive) · 0bf545f1ebcb90c5 · report fixture: returned PointNetMLP · level recorded 2026-09-22
aviros/pointnet_totations community (archive-listed) 1 sample, 0 ran · 1 unverified
get_model in 368 papers models/pointnet_cls.py unverified licence not identified · pointer only · 48af9922c4bc65ce · report
brendanmallery9/entropic-barycenters community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
PointNet in 5 papers classification_example/pointnet_implementation.py ran fingerprinted MIT (permissive) · df9cbdf65f14db23 · report fixture: returned PointNet · level recorded 2026-09-22
Tnet classification_example/pointnet_implementation.py ran fingerprinted MIT (permissive) · 9b8bdedaae9abf63 · report fixture: returned Tnet · level recorded 2026-09-22
Transform classification_example/pointnet_implementation.py ran fingerprinted MIT (permissive) · cfb8085f652dcf26 · report fixture: returned Transform · level recorded 2026-09-22
donshen/pointnet.phasedetection community (archive-listed) 1 sample, 0 ran · 1 unverified
PointNetfeat pointnet/model.py unverified no licence file found · pointer only · a38f869df6ca0b28 · report
ftdlyc/pointnet_pytorch community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PointNetClassify models/pointnet.py ran fingerprinted no licence file found · pointer only · 05f62796540f4175 · report fixture: returned PointNetClassify · level recorded 2026-09-22
TNet models/pointnet.py ran fingerprinted no licence file found · pointer only · 58ce72343decd663 · report fixture: returned TNet · level recorded 2026-09-22
hnmspirit/pointnet1 community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
PointNetCls pointnet.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 98f3e76878c4c84f · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PointNetFeat pointnet.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 5f85b825ddcf36f0 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
STN3d pointnet.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 383dbc340bd8d282 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
lingzhang1/pointnet_pytorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
PointNetCls pointnet.py ran · metamorphic tier: deterministic MIT (permissive) · 21086233dee4a940 · report fixture: returned PointNetCls · level recorded 2026-09-22
PointNetfeat pointnet.py ran · metamorphic tier: deterministic MIT (permissive) · 4974babafbd20779 · report fixture: returned PointNetfeat · level recorded 2026-09-22
STN3d pointnet.py ran · metamorphic tier: deterministic MIT (permissive) · 83226be05a2733e2 · report fixture: returned STN3d · level recorded 2026-09-22
lingzhang1/pointnet_tensorflow community (archive-listed) 4 samples, 0 ran · 4 unverified
avg_pool2d models/pointnet_cls.py unverified licence not identified · pointer only · e571fd880c2dbdd3 · report
feature_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · e76279c115b28343 · report
get_model in 368 papers models/pointnet_cls.py unverified licence not identified · pointer only · 95a4db623125d0e2 · report
input_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · f0e4dc318402cad6 · report
mengxingshifen1218/pointnet.pytorch community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
PointNetfeat pointnet/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 354def71e0aa90c3 · report fixture: returned PointNetfeat · level recorded 2026-09-22
STN3d pointnet/model.py ran fingerprinted MIT (permissive) · c44477c4a9ec175d · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
STNkd pointnet/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · b95fe13373b6da5e · report fixture: returned STNkd · level recorded 2026-09-22
PointNetCls pointnet/model.py unverified MIT (permissive) · 36089440508002ef · report
minhncedutw/pointnet1_keras community (archive-listed) 5 samples, 3 ran (3 instrument-failed) · 2 unverified
extend_dimension pointnet.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 0ae39a94cbae41ee · report fixture: signature global_feature:EagerTensor/2/float, axis:int/0/int · returned EagerTensor · level recorded 2026-09-22
extend_size pointnet.py ran; the contract check could not run (RAISES) MIT (permissive) · 17e91095a5bf4806 · report fixture: signature global_feature:EagerTensor/3/float, num_points:int/0/int · returned EagerTensor · level recorded 2026-09-22
multilayer_perceptron pointnet.py ran; the contract check could not run (RAISES) MIT (permissive) · 873db57e4b207f27 · report fixture: signature inputs:KerasTensor/0/float, mlp_nodes:list/1/int · returned list · level recorded 2026-09-24
PointNetFull pointnet.py unverified MIT (permissive) · 2b9287ed2f1201ad · report
TNet pointnet.py unverified MIT (permissive) · a7401c0d157e19a0 · report
nikitakaraevv/pointnet community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
PointNet in 5 papers source/model.py ran fingerprinted Apache-2.0 (permissive) · 0bb3296226c3f2e6 · report fixture: signature input:Tensor/3/float · returned tuple · level recorded 2026-09-22
Tnet source/model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 8de6ad0849c28980 · report fixture: signature input:Tensor/3/float · returned Tensor · level recorded 2026-09-22
Transform source/model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 65aa5b5bf3ec8b52 · report fixture: signature input:Tensor/3/float · returned tuple · level recorded 2026-09-22
opeco17/pointnet community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
FeatureTNet model.py ran no licence file found · pointer only · f153c54ecb32c4eb · report fixture: returned FeatureTNet · level recorded 2026-09-22
InputTNet model.py ran no licence file found · pointer only · f7820c2d16a9147f · report fixture: returned InputTNet · level recorded 2026-09-22
MaxPool model.py ran fingerprinted no licence file found · pointer only · 0bcd28a18c4f1eac · report fixture: returned MaxPool · level recorded 2026-09-22
NonLinear model.py ran fingerprinted no licence file found · pointer only · 44f26f82c86e21d7 · report fixture: returned NonLinear · level recorded 2026-09-22
PointNet in 5 papers model.py ran no licence file found · pointer only · f926ecb7397001aa · report fixture: returned PointNet · level recorded 2026-09-22
prasadsawant5/PointNet community (archive-listed) 4 samples, 0 ran · 4 unverified
CustomConv model/model.py unverified no licence file found · pointer only · 0f43a168cc1824d7 · report
CustomDense model/model.py unverified no licence file found · pointer only · 2f39ebb16cb20629 · report
TNet model/model.py unverified no licence file found · pointer only · e83b39fb561c32b6 · report
get_model in 368 papers model/model.py unverified no licence file found · pointer only · da5a9b32e3d1a0b7 · report
romaintha/pytorch_pointnet community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
BasePointNet model/pointnet.py ran MIT (permissive) · 6a7f90648d711cdc · report fixture: returned BasePointNet · level recorded 2026-09-22
ClassificationPointNet model/pointnet.py ran MIT (permissive) · 0ba84a38091fc6f1 · report fixture: returned ClassificationPointNet · level recorded 2026-09-22
TransformationNet model/pointnet.py ran MIT (permissive) · f9d3c61b90e69369 · report fixture: returned TransformationNet · level recorded 2026-09-22
sarthakTUM/roofn3d community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PointNetfeat cls_seg_mt/pointnet.py ran fingerprinted no licence file found · pointer only · 79e1c88294831c30 · report fixture: returned PointNetfeat · level recorded 2026-09-22
smfirmin/DeepLearningFinalProject community (archive-listed) 6 samples, 3 ran (0 instrument-failed) · 3 unverified
AttnEncoderBlock pointnet/model.py ran · metamorphic tier: invariant MIT (permissive) · 89dc188151d58f24 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
STN3d pointnet/model.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · daf339afe5dff1a4 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
STNkd pointnet/model.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 9002018eae6ef27f · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PointNet in 5 papers pointnet/model.py unverified MIT (permissive) · 59d97f829f142dbb · report
PointNetCls pointnet/model.py unverified MIT (permissive) · 284ff4abcf8b1064 · report
PointNetfeat pointnet/model.py unverified MIT (permissive) · d6ce0c8c791bfaa9 · report
soumik12345/point-cloud-segmentation community (archive-listed) 6 samples, 5 ran (4 instrument-failed) · 1 unverified
OrthogonalRegularizer point_seg/pointnet/models.py ran MIT (permissive) · 63fc528b5460f4b1 · report fixture: returned OrthogonalRegularizer · level recorded 2026-09-22
conv_block in 95 papers point_seg/pointnet/models.py ran; the contract check could not run (RAISES) MIT (permissive) · 2a7d70d6b0134a2a · report fixture: signature x:SymbolicTensor/3/float, filters:int/0/int, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
mlp_block point_seg/pointnet/models.py ran; the contract check could not run (RAISES) MIT (permissive) · f3daa006cbd462f9 · report fixture: signature x:SymbolicTensor/2/float, filters:int/0/int, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
transformation_block point_seg/pointnet/models.py ran; the contract check could not run (RAISES) MIT (permissive) · d8cd548d30495e3a · report fixture: signature inputs:SymbolicTensor/3/float, num_features:int/0/int, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
transformation_net point_seg/pointnet/models.py ran; the contract check could not run (RAISES) MIT (permissive) · 0f3baaf068f79aef · report fixture: signature inputs:SymbolicTensor/3/float, num_features:int/0/int, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
get_shape_segmentation_model point_seg/pointnet/models.py unverified MIT (permissive) · b6e93dd403cca1b8 · report
vinits5/learning3d community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PointNet in 5 papers models/pointnet.py ran · metamorphic tier: deterministic MIT (permissive) · 90de9a977caa457e · report fixture: returned PointNet · level recorded 2026-09-22
Pooling in 6 papers models/pointnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 73fbe9c91fe32ceb · report fixture: returned Pooling · level recorded 2026-09-22
xurui1217/pointnet.pytorch-master community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PointNetfeat pointnet.py ran fingerprinted MIT (permissive) · 65e190258615dca9 · report fixture: returned PointNetfeat · level recorded 2026-09-22
y2kmz/pointnetv2 community (archive-listed) 8 samples, 4 ran (4 instrument-failed) · 4 unverified
batch_norm_for_conv2d models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · 490ceafb5b7bef9e · report fixture: signature inputs:SymbolicTensor/4/float, is_training:ResourceVariable/0/bool, bn_decay:float/0/float, scope:str/0/str · returned SymbolicTensor · level recorded 2026-09-22
batch_norm_for_fc models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · 5c479cbe546cf012 · report fixture: signature inputs:SymbolicTensor/2/float, is_training:SymbolicTensor/0/bool, bn_decay:float/0/float, scope:str/0/str · returned SymbolicTensor · level recorded 2026-09-22
batch_norm_template models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · 37a2ce29ed97f4cf · report fixture: signature inputs:SymbolicTensor/4/float, is_training:SymbolicTensor/0/bool, scope:str/0/str, moments_dims:list/1/int, bn_decay:float/0/float · returned SymbolicTensor · level recorded 2026-09-22
fully_connected in 9 papers models/pointnet_cls.py ran · our draft was wrong licence not identified · pointer only · 574c1fa1a7e92c2c · report fixture: signature inputs:SymbolicTensor/2/float, num_outputs:int/0/int, scope:str/0/str, use_xavier:bool/0/bool, stddev:float/0/float, weight_decay:float/0/float, activation_fn:callable/0/?, bn:bool/0/bool, bn_decay:float/0/float, is_training:SymbolicTensor/0/bool · returned SymbolicTensor · level recorded 2026-09-22
conv2d in 119 papers models/pointnet_cls.py unverified licence not identified · pointer only · 6936701115e232ad · report
feature_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · 10c5b66ad263ff7e · report
get_model in 368 papers models/pointnet_cls.py unverified licence not identified · pointer only · dd14f2ef42a37ac6 · report
input_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · e2ff26c38b1f7d9c · report
yangyucheng000/pointnet community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
load_bin_file EGnet/postprocess.py ran Apache-2.0 (permissive) · fd1399c5facd09f5 · report fixture: signature bin_file:str/0/str, shape:tuple/1/int, dtype:str/0/str · returned ndarray · level recorded 2026-09-26
parse in 85 papers EGnet/postprocess.py ran Apache-2.0 (permissive) · 3d6091bb44a57125 · report fixture: signature arg:list/1/str · returned Namespace · level recorded 2026-09-26
scan_dir EGnet/postprocess.py ran Apache-2.0 (permissive) · 33ece3afadf6ad33 · report fixture: signature bin_path:str/0/str · returned list · level recorded 2026-09-26
yanxp/PointNet community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PointNetfeat model/pointnet.py ran no licence file found · pointer only · 674ede50cbdb04c2 · report fixture: returned PointNetfeat · level recorded 2026-09-22
TransLayer in 8 papers model/pointnet.py ran no licence file found · pointer only · d22507edb8c91af0 · report fixture: returned TransLayer · level recorded 2026-09-22
zgx0534/pointnet_win community (archive-listed) 2 samples, 0 ran · 2 unverified
get_model in 368 papers models/pointnet_cls.py unverified licence not identified · pointer only · 4ec85cac3606dfa6 · report
input_transform_net models/pointnet_cls.py unverified licence not identified · pointer only · 39d0e1d18ec01e27 · report
debajyotid2/pointnet_pl community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · b5cf4f63f0bd5977 · report fixture: returned ConvBlock · level recorded 2026-09-22
FCBlock in 8 papers src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · c0998ae0e66ae44b · report fixture: returned FCBlock · level recorded 2026-09-22
PointNetClassifier src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 86c240d726febafb · report fixture: returned PointNetClassifier · level recorded 2026-09-22
Transpose in 9 papers src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 0ac9e981b1b6e263 · report fixture: returned Transpose · level recorded 2026-09-22
princeton-vl/SimpleView community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PointNetfeat pointnet_pyt/pointnet/model.py ran fingerprinted BSD-3-Clause (permissive) · 3ce362b43484ed47 · report fixture: returned PointNetfeat · level recorded 2026-09-22
STNkd pointnet_pyt/pointnet/model.py ran BSD-3-Clause (permissive) · 9198530155430cd2 · report fixture: returned STNkd · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

39 assemblies on this paper: 39 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

39 sibling assemblies for PointNet (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 39 sibling assemblies; the other 27 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for PointNet (graph method: PointNet). 12 bricks; individually on a fixture: 0 ran · 12 unverified. The assembly has not been run end-to-end.

one of 39 siblings

  1. get_model entry · level 0 · unverified · 3348d605b8bb0364
  2. conv2d helper · level 0 · unverified · 3471f8d470b6a58d
  3. dropout helper · level 0 · unverified · c59b25c37b041301
  4. feature_transform_net model · level 0 · unverified · c208adaa3faf9c5c
  5. fully_connected helper · level 0 · unverified · 5a22ecfcfb8dd56f
  6. input_transform_net model · level 0 · unverified · 53ab45fb2b1c27fb
  7. max_pool2d helper · level 0 · unverified · ceb4bc5d5bdb28a9
  8. _variable_on_cpu helper · level 0 · unverified · 0e8b6b26d8827177
  9. _variable_with_weight_decay helper · level 0 · unverified · cd31f214652ec580
  10. batch_norm_for_conv2d helper · level 0 · unverified · e767d7c8946f4c9a
  11. batch_norm_for_fc helper · level 0 · unverified · 5cf119ef55c54349
  12. batch_norm_template helper · level 0 · unverified · 1e3a7b062fd34628

harvested Assembly for PointNet (graph method: PointNet). 4 bricks; individually on a fixture: 0 ran · 4 unverified. The assembly has not been run end-to-end.

one of 39 siblings

  1. pointnet_cls entry · level 0 · unverified · 17058c05afc3f8c5
  2. t_net helper · level 0 · unverified · 53fb6fa3c4fbe5f3
  3. orthogonality_reg helper · level 0 · unverified · f703b64c37ee8c75
  4. frobenius_norm helper · level 0 · unverified · b326dccf1b38873f

harvested Assembly for PointNet (graph method: PointNet). 4 bricks; individually on a fixture: 0 ran · 4 unverified. The assembly has not been run end-to-end.

one of 39 siblings

  1. get_model entry · level 0 · unverified · da5a9b32e3d1a0b7
  2. CustomConv helper · level 0 · unverified · 0f43a168cc1824d7
  3. CustomDense helper · level 0 · unverified · 2f39ebb16cb20629
  4. TNet model · level 0 · unverified · e83b39fb561c32b6

harvested Assembly for PointNet (graph method: PointNet). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 39 siblings

  1. PointNet entry · level 1 · ran · 90de9a977caa457e
  2. Pooling helper · level 1 · ran · 73fbe9c91fe32ceb

harvested Assembly for PointNet (graph method: PointNet). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 39 siblings

  1. PointNetMLP entry · level 1 · ran · 0bf545f1ebcb90c5

harvested Assembly for PointNet (graph method: PointNet). 4 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 39 siblings

  1. PointNetCls entry · level 0 · unverified · 36089440508002ef
  2. PointNetfeat model · level 1 · ran · 354def71e0aa90c3
  3. STN3d model · level 1 · ran · c44477c4a9ec175d
  4. STNkd helper · level 1 · ran · b95fe13373b6da5e

harvested Assembly for PointNet (graph method: PointNet). 12 bricks; individually on a fixture: 0 ran · 12 unverified. The assembly has not been run end-to-end.

one of 39 siblings

  1. get_model entry · level 0 · unverified · ebf79aab4c147450
  2. conv2d helper · level 0 · unverified · 3471f8d470b6a58d
  3. dropout helper · level 0 · unverified · c59b25c37b041301
  4. feature_transform_net helper · level 0 · unverified · c208adaa3faf9c5c
  5. fully_connected helper · level 0 · unverified · 5a22ecfcfb8dd56f
  6. input_transform_net helper · level 0 · unverified · 53ab45fb2b1c27fb
  7. max_pool2d helper · level 0 · unverified · ceb4bc5d5bdb28a9
  8. _variable_on_cpu helper · level 0 · unverified · 0e8b6b26d8827177
  9. _variable_with_weight_decay helper · level 0 · unverified · cd31f214652ec580
  10. batch_norm_for_conv2d helper · level 0 · unverified · e767d7c8946f4c9a
  11. batch_norm_for_fc helper · level 0 · unverified · 5cf119ef55c54349
  12. batch_norm_template helper · level 0 · unverified · 1e3a7b062fd34628

harvested Assembly for PointNet (graph method: PointNet). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 39 siblings

  1. PointNet entry · level 1 · ran · d49fb29dc696ee6c

harvested Assembly for PointNet (graph method: PointNet). 12 bricks; individually on a fixture: 0 ran · 12 unverified. The assembly has not been run end-to-end.

one of 39 siblings

  1. get_model entry · level 0 · unverified · 4ec85cac3606dfa6
  2. conv2d helper · level 0 · unverified · 3471f8d470b6a58d
  3. dropout helper · level 0 · unverified · c59b25c37b041301
  4. feature_transform_net helper · level 0 · unverified · c208adaa3faf9c5c
  5. fully_connected helper · level 0 · unverified · 5a22ecfcfb8dd56f
  6. input_transform_net helper · level 0 · unverified · 39d0e1d18ec01e27
  7. max_pool2d helper · level 0 · unverified · ceb4bc5d5bdb28a9
  8. _variable_on_cpu helper · level 0 · unverified · 0e8b6b26d8827177
  9. _variable_with_weight_decay helper · level 0 · unverified · cd31f214652ec580
  10. batch_norm_for_conv2d helper · level 0 · unverified · e767d7c8946f4c9a
  11. batch_norm_for_fc helper · level 0 · unverified · 5cf119ef55c54349
  12. batch_norm_template helper · level 0 · unverified · 1e3a7b062fd34628

harvested Assembly for PointNet (graph method: PointNet). 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 39 siblings

  1. PointNetClassifier entry · level 1 · ran · 86c240d726febafb
  2. ConvBlock model · level 1 · ran · b5cf4f63f0bd5977
  3. FCBlock model · level 1 · ran · c0998ae0e66ae44b
  4. Transpose helper · level 1 · ran · 0ac9e981b1b6e263

harvested Assembly for PointNet (graph method: PointNet). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 39 siblings

  1. PointNetCls entry · level 1 · ran · 21086233dee4a940
  2. PointNetfeat model · level 1 · ran · 4974babafbd20779
  3. STN3d model · level 1 · ran · 83226be05a2733e2

harvested Assembly for PointNet (graph method: PointNet). 12 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 39 siblings

  1. get_model entry · level 0 · unverified · 1a2be9b9d77bfa7e
  2. conv2d helper · level 0 · unverified · 0ed2449abae99e7d
  3. dropout helper · level 1 · ran · our draft was wrong · b9cc54403e6c3be8
  4. feature_transform_net model · level 0 · unverified · 2862f30a5a09b5f0
  5. fully_connected helper · level 0 · unverified · 85a6137807ce8849
  6. input_transform_net model · level 0 · unverified · 096e87fb2226873a
  7. max_pool2d helper · level 1 · ran · our draft was wrong · 367777b5febe9b58
  8. _variable_on_cpu helper · level 1 · ran; the contract check could not run (RAISES) · 26d314e83af41fab
  9. _variable_with_weight_decay helper · level 1 · ran; the contract check could not run (RAISES) · 87f93d0c7129ee4e
  10. batch_norm_for_conv2d helper · level 0 · unverified · 762f096e29d11bf9
  11. batch_norm_for_fc helper · level 0 · unverified · e25a0bc56534a31f
  12. batch_norm_template helper · level 0 · unverified · 88e171f204372a23
  1. PointNetfeat · 5ac8de9dc509e673 · 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. PointNetCls · 5f7146bb91bfa983 · 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. PointNetCls · 63685ed96338dc10 · 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. PointNetfeat · 6d79b2a387308574 · 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. PointNetfeat · 6edf40f9b6ed3bee · 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. PointNetCls · 7314496e510f7c93 · 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. PointNetfeat · 7a3e46bc5c26a6d1 · 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. get_model · 875b9b694f34a6b2 · 13 bricks; individually on a fixture: 0 ran · 13 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. PointNetfeat · 8c0fc9f6da5a0fd7 · 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. create_pointnet · 9106c9ec1d228a88 · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. PointNetClassify · 99cc0ea257229c52 · 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. ClassificationPointNet · a8fb1e2e6e3056cf · 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. PointNet · ae6ad7c84ff6319e · 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
  14. get_model · b1c2cec1027fa8f5 · 12 bricks; individually on a fixture: 8 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[25] in the JSON twin
  15. PointNetfeat · b595362e61a3f94e · 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[26] in the JSON twin
  16. PointNet · b60d827211c621ab · 5 bricks; individually on a fixture: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[27] in the JSON twin
  17. get_shape_segmentation_model · bac95266a21949f0 · 6 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[28] in the JSON twin
  18. get_model · bb8d788ec3333f11 · 12 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
  19. PointNetCls · cdee7e9777a27ecd · 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[30] in the JSON twin
  20. PointNetfeat · d776385c495a8c97 · 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[31] in the JSON twin
  21. PointNetfeat · e0f7e71e2c38ff7b · 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[32] in the JSON twin
  22. PointNet · e33e24dd4aae8a98 · 6 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
  23. get_model · e5af3199c5c4aff0 · 11 bricks; individually on a fixture: 0 ran · 11 unverified · The assembly has not been run end-to-end · assemblies[34] in the JSON twin
  24. PointNetSeg · e614888028ed4032 · 6 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[35] in the JSON twin
  25. PointNet · e74258efe5d995c6 · 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[36] in the JSON twin
  26. get_model · e7a6c898280785a5 · 11 bricks; individually on a fixture: 0 ran · 11 unverified · The assembly has not been run end-to-end · assemblies[37] in the JSON twin
  27. PointNetFull · fa8af41ff975a7f1 · 5 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[38] in the JSON twin

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1612.00593") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Face Reconstruction3D Semantic SegmentationFew-Shot 3D Point Cloud ClassificationPoint Cloud SegmentationScene SegmentationSemantic ParsingSemantic SegmentationSkeleton Based Action RecognitionSupervised Only 3D Point Cloud Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Face Reconstruction !(()&&!|*|*| po 0L po #1 of 1 Archive leaderboard report
3D Part Segmentation IntrA PointNet DSC (A) 49.59 #7 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointNet DSC (V) 85.00 #7 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointNet IoU (A) 37.75 #7 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointNet IoU (V) 75.23 #7 of 7 Archive leaderboard report
3D Part Segmentation ShapeNet-Part PointNet Instance Average IoU 83.7 #63 of 67 Archive leaderboard report
3D Point Cloud Classification IntrA PointNet F1 score (5-fold) 0.684 #12 of 12 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointNet Mean Accuracy 86.0 #105 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointNet Number of params 3.47M #105 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointNet Overall Accuracy 89.2 #105 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40-C PointNet Error Rate 0.283 #13 of 13 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointNet Mean Accuracy 63.4 #76 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointNet Overall Accuracy 68.2 #76 of 77 Archive leaderboard report
3D Semantic Segmentation KITTI-360 PointNet Model size N/A #4 of 8 Archive leaderboard report
3D Semantic Segmentation KITTI-360 PointNet mIoU Category 30.42 #4 of 8 Archive leaderboard report
3D Semantic Segmentation KITTI-360 PointNet miou 13.07 #4 of 8 Archive leaderboard report
3D Semantic Segmentation SemanticKITTI PointNet test mIoU 14.6% #41 of 45 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) PointNet Overall Accuracy 46.60 #29 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) PointNet Standard Deviation 13.5 #29 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) PointNet Overall Accuracy 35.20 #29 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) PointNet Standard Deviation 13.5 #29 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) PointNet Overall Accuracy 51.97 #28 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) PointNet Standard Deviation 12.1 #28 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) PointNet Overall Accuracy 57.81 #28 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) PointNet Standard Deviation 15.5 #28 of 30 Archive leaderboard report
Point Cloud Classification PointCloud-C PointNet mean Corruption Error (mCE) 1.422 #24 of 24 Archive leaderboard report
Point Cloud Segmentation PointCloud-C PointNet mean Corruption Error (mCE) 1.178 #11 of 11 Archive leaderboard report
Scene Segmentation ScanNet PointNet++ Average Accuracy 60.2% #2 of 3 Archive leaderboard report
Semantic Segmentation S3DIS PointNet Number of params N/A #53 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointNet mAcc 66.2 #53 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointNet Number of params N/A #59 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointNet mAcc 49.0 #59 of 61 Archive leaderboard report
Skeleton Based Action Recognition CAD-120 PointNet (5-shot) Accuracy 69.1% #7 of 8 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN PointNet GFLOPs 0.5 #12 of 12 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN PointNet Number of params (M) 3.5 #12 of 12 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN PointNet Overall Accuracy (PB_T50_RS) 68.0 #12 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections