Papers › Dynamic Graph CNN for Learning on Point Clouds

Dynamic Graph CNN for Learning on Point Clouds

24 Jan 2018arXiv:1801.07829archive 2025-07-28

Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon

Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long been proposed in graphics and vision, however, the recent overwhelming success of convolutional neural networks (CNNs) for image analysis suggests the value of adapting insight from CNN to the point cloud world. Point clouds inherently lack topological information so designing a model to recover topology can enrich the representation power of point clouds. To this end, we propose a new neural network module dubbed EdgeConv suitable for CNN-based high-level tasks on point clouds including classification and segmentation. EdgeConv acts on graphs dynamically computed in each layer of the network. It is differentiable and can be plugged into existing architectures. Compared to existing modules operating in extrinsic space or treating each point independently, EdgeConv has several appealing properties: It incorporates local neighborhood information; it can be stacked applied to learn global shape properties; and in multi-layer systems affinity in feature space captures semantic characteristics over potentially long distances in the original embedding. We show the performance of our model on standard benchmarks including ModelNet40, ShapeNetPart, and S3DIS.

PaperPDFCodeCode 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 44 code samples harvested from 10 repositories linked to this paper: 16 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 28 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 7 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 43 samples from 9 repositories, 15 ran (6 with no instrument failure; 9 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

WangYueFt/dgcnn officialmentioned in papermentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
AmitBracha/GIP_project mentioned on GitHubtfSyntology: 17 samples, 1 ran (1 instrument-failed) · 16 unverified report
AnTao97/dgcnn.pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
JingfeiHuang/DGCNN-Paddle mentioned on GitHubpaddleSyntology: not harvested report
Squanch-U/DGCNN mentioned on GitHubmindsporeSyntology: not harvested report
af13s/dgcnn-amino mentioned on GitHubtfSyntology: 12 samples, 1 ran (1 instrument-failed) · 11 unverified report
brent-murray/tr3d_pointaugdgcnn mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
bupt-gamma/gammagl mentioned on GitHubtfSyntology: not harvested report
cy-xu/spatially_aware_ai mentioned on GitHubpytorchAGPL-3.0Syntology: not harvested report
hansen7/NRS_3D mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
hqucms/ParticleNet mentioned on GitHubtfSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
lingzhang1/ContrastNet mentioned on GitHubtfSyntology: not harvested report
lingzhang1/dgcnn_sampling mentioned on GitHubtfSyntology: not harvested report
lingzhang1/dgcnn_v2 mentioned on GitHubtfSyntology: not harvested report
nnn911/MLSI mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
vinits5/learning3d mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
xrndai/dgcnn_amino_acid_structure mentioned on GitHubtfSyntology: not harvested report
yossilevii100/critical_points2 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robustifying Point Cloud Networks by Refocusing (arXiv:2308.05525; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
yossilevii100/refocusing mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robustifying Point Cloud Networks by Refocusing (arXiv:2308.05525; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
gitee.com/gai-shaoyan/mind3d Syntology: not harvested report
princeton-vl/SimpleView pytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified 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

44 samples harvested: 16 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 28 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
7ran; the contract check could not run
7ran
28unverified

Licence: 31 of the 44 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 10 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 4 samples that ran, the graph records a signature this page does not show: 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. “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.

WangYueFt/dgcnn official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DGCNN in 6 papers pytorch/model.py ran MIT (permissive) · bd4d12ec0ab7479e · report fixture: returned DGCNN · level recorded 2026-09-22
AmitBracha/GIP_project community (archive-listed) 17 samples, 1 ran (1 instrument-failed) · 16 unverified
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
models/dgcnn.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · afa67b67c8fbe518 · report fixture: signature adj_matrix:EagerTensor/3/float, k:int/0/int · returned SymbolicTensor · level recorded 2026-09-22
_variable_on_cpu models/dgcnn.py unverified no licence file found · pointer only · adf5846b3d969f1f · report
_variable_with_weight_decay models/dgcnn.py unverified no licence file found · pointer only · 469a43579e0ab430 · report
batch_norm_dist_template models/dgcnn.py unverified no licence file found · pointer only · e836d5d02fbe1569 · report
batch_norm_for_conv2d models/dgcnn.py unverified no licence file found · pointer only · aa9412f2d47b5c71 · report
batch_norm_for_fc models/dgcnn.py unverified no licence file found · pointer only · 8563d3c5e43f3c8d · report
batch_norm_template models/dgcnn.py unverified no licence file found · pointer only · df7b6d675ad1faf4 · report
conv2d in 119 papers models/dgcnn.py unverified no licence file found · pointer only · 5caf714eb8eb5aa5 · report
dropout in 34 papers models/dgcnn.py unverified no licence file found · pointer only · a7e0217e7e46649e · report
fully_connected in 9 papers models/dgcnn.py unverified no licence file found · pointer only · 65878b612b525cd9 · report
get_edge_feature in 5 papers models/dgcnn.py unverified no licence file found · pointer only · f7b114580fc34243 · report
get_edge_feature_fc_momentum models/dgcnn.py unverified no licence file found · pointer only · a3b270bbc3562938 · report
get_model in 368 papers models/dgcnn.py unverified no licence file found · pointer only · aa032686f869c6ca · report
get_tensor_second_momentum models/dgcnn.py unverified no licence file found · pointer only · 3554079d199ef44d · report
input_transform_net models/dgcnn.py unverified no licence file found · pointer only · d07227089f4eb7c0 · report
max_pool2d models/dgcnn.py unverified no licence file found · pointer only · 5bd4731c81b94fda · report
AnTao97/dgcnn.pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DGCNN_cls model.py ran MIT (permissive) · deae149da586b0cb · report fixture: returned DGCNN_cls · level recorded 2026-09-22
af13s/dgcnn-amino community (archive-listed) 12 samples, 1 ran (1 instrument-failed) · 11 unverified
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
models/dgcnn.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 9000f8e3010b8eb7 · report fixture: signature adj_matrix:EagerTensor/3/float, k:int/0/int · returned EagerTensor · level recorded 2026-09-22
_variable_on_cpu models/dgcnn.py unverified no licence file found · pointer only · 2918d47029a9f7b8 · report
_variable_with_weight_decay models/dgcnn.py unverified no licence file found · pointer only · 095d661fc452344e · report
batch_norm_dist_template models/dgcnn.py unverified no licence file found · pointer only · bd5dd2c726337fbb · report
batch_norm_for_conv2d models/dgcnn.py unverified no licence file found · pointer only · 278e89613b2fcc9d · report
batch_norm_for_fc models/dgcnn.py unverified no licence file found · pointer only · 3e5a9afaceaecb8e · report
conv2d in 119 papers models/dgcnn.py unverified no licence file found · pointer only · 2f2a5221e029473a · report
fully_connected in 9 papers models/dgcnn.py unverified no licence file found · pointer only · 40bf1749410aa96f · report
get_edge_feature in 5 papers models/dgcnn.py unverified no licence file found · pointer only · afb21d6165856bb0 · report
get_model in 368 papers models/dgcnn.py unverified no licence file found · pointer only · b15247159c9e74bf · report
input_transform_net models/dgcnn.py unverified no licence file found · pointer only · c5549fd76a62a77a · report
brent-murray/tr3d_pointaugdgcnn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DGCNN in 6 papers models/dgcnn.py ran fingerprinted no licence file found · pointer only · 105ce77f02aa8fc3 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
hansen7/NRS_3D community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
DGCNN in 6 papers models/dgcnn_cls.py ran MIT (permissive) · 5225ebf366dff39c · report fixture: returned DGCNN · level recorded 2026-09-22
get_graph_feature in 51 papers
census: 6 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32
models/dgcnn_cls.py ran · our draft was wrong MIT (permissive) · ffacb4286b9c5b79 · report fixture: signature x:Tensor/3/float, k:int/0/int, idx:NoneType/0/? · returned Tensor · level recorded 2026-09-22
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 3, kind float, dtype float32
models/dgcnn_cls.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 999b1b3194e7ace2 · report fixture: signature x:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-22
hqucms/ParticleNet community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
batch_distance_matrix_general tf-keras/tf_keras_model.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 4db0912e4435ab42 · report fixture: signature A:EagerTensor/3/float, B:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-22
edge_conv tf-keras/tf_keras_model.py ran; the contract check could not run (RAISES) MIT (permissive) · 32c56f6033c6d2fb · report fixture: signature points:EagerTensor/3/float, features:EagerTensor/3/float, num_points:int/0/int, K:int/0/int, channels:tuple/1/int, with_bn:bool/0/bool, activation:str/0/str, pooling:str/0/str, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
tf-keras/tf_keras_model.py ran MIT (permissive) · 86fd210ea5960f23 · report fixture: returned SymbolicTensor · level recorded 2026-09-22
nnn911/MLSI community (archive-listed) 1 sample, 0 ran · 1 unverified
DGCNN_cls src/MLSI/DG_CNN_tools.py unverified licence not identified · pointer only · 340df50c5fa6ae0a · report
vinits5/learning3d community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
DGCNN in 6 papers models/dgcnn.py ran MIT (permissive) · f746806bd48762f6 · report fixture: returned DGCNN · level recorded 2026-09-22
get_graph_feature in 51 papers
census: 6 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32
models/dgcnn.py ran · our draft was wrong MIT (permissive) · 26b869462d7d37e6 · report fixture: signature x:Tensor/3/float, k:int/0/int, device:NoneType/0/? · returned Tensor · level recorded 2026-09-22
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 3, kind float, dtype float32
models/dgcnn.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · ee7b4d081c1fd7b3 · report fixture: signature x:Tensor/3/float, k:int/0/int, add_one_to_k:bool/0/bool · returned Tensor · level recorded 2026-09-22
princeton-vl/SimpleView community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
DGCNN in 6 papers dgcnn/pytorch/model.py ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · ad3b789a1f825e88 · report fixture: returned DGCNN · level recorded 2026-09-22
get_graph_feature in 51 papers
census: 6 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32
dgcnn/pytorch/model.py ran; the contract check could not run (RAISES) BSD-3-Clause (permissive) · 9a8756778dd8234a · report fixture: returned Tensor · 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.

11 assemblies on this paper: 11 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

11 sibling assemblies for Edge-Conv (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DGCNN_cls entry · level 0 · unverified · 340df50c5fa6ae0a

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 17 bricks; individually on a fixture: 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) · 16 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. get_model entry · level 0 · unverified · aa032686f869c6ca
  2. conv2d helper · level 0 · unverified · 5caf714eb8eb5aa5
  3. dropout helper · level 0 · unverified · a7e0217e7e46649e
  4. fully_connected helper · level 0 · unverified · 65878b612b525cd9
  5. get_edge_feature helper · level 0 · unverified · f7b114580fc34243
  6. get_edge_feature_fc_momentum helper · level 0 · unverified · a3b270bbc3562938
  7. input_transform_net model · level 0 · unverified · d07227089f4eb7c0
  8. knn helper · level 1 · ran; the contract check could not run (RAISES) · afa67b67c8fbe518
  9. pairwise_distance helper · level 0 · unverified · c849266d759a5b88
  10. _variable_on_cpu helper · level 0 · unverified · adf5846b3d969f1f
  11. _variable_with_weight_decay helper · level 0 · unverified · 469a43579e0ab430
  12. batch_norm_for_conv2d helper · level 0 · unverified · aa9412f2d47b5c71
  13. batch_norm_for_fc helper · level 0 · unverified · 8563d3c5e43f3c8d
  14. get_tensor_second_momentum helper · level 0 · unverified · 3554079d199ef44d
  15. max_pool2d helper · level 0 · unverified · 5bd4731c81b94fda
  16. batch_norm_dist_template helper · level 0 · unverified · e836d5d02fbe1569
  17. batch_norm_template helper · level 0 · unverified · df7b6d675ad1faf4

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DGCNN entry · level 1 · ran · ad3b789a1f825e88
  2. get_graph_feature helper · level 1 · ran; the contract check could not run (RAISES) · 9a8756778dd8234a
  3. knn helper · level 1 · ran; the contract check could not run · cdd0141594039dcb

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 15 bricks; individually on a fixture: 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) · 14 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. get_model entry · level 0 · unverified · b15247159c9e74bf
  2. conv2d helper · level 0 · unverified · 2f2a5221e029473a
  3. dropout helper · level 0 · unverified · c59b25c37b041301
  4. fully_connected helper · level 0 · unverified · 40bf1749410aa96f
  5. get_edge_feature helper · level 0 · unverified · afb21d6165856bb0
  6. input_transform_net helper · level 0 · unverified · c5549fd76a62a77a
  7. knn helper · level 1 · ran; the contract check could not run (RAISES) · 9000f8e3010b8eb7
  8. pairwise_distance helper · level 0 · unverified · 3d90b05b13b0c0b9
  9. _variable_on_cpu helper · level 0 · unverified · 2918d47029a9f7b8
  10. _variable_with_weight_decay helper · level 0 · unverified · 095d661fc452344e
  11. batch_norm_for_conv2d helper · level 0 · unverified · 278e89613b2fcc9d
  12. batch_norm_for_fc helper · level 0 · unverified · 3e5a9afaceaecb8e
  13. max_pool2d helper · level 0 · unverified · ceb4bc5d5bdb28a9
  14. batch_norm_dist_template helper · level 0 · unverified · bd5dd2c726337fbb
  15. batch_norm_template helper · level 0 · unverified · 1e3a7b062fd34628

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DGCNN entry · level 1 · ran · bd4d12ec0ab7479e
  2. get_graph_feature helper · level 1 · ran; the contract check could not run (RAISES) · 9a8756778dd8234a
  3. knn helper · level 1 · ran; the contract check could not run · cdd0141594039dcb

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. edge_conv entry · level 1 · ran; the contract check could not run (RAISES) · 32c56f6033c6d2fb
  2. batch_distance_matrix_general helper · level 1 · ran; the contract check could not run (RAISES) · 4db0912e4435ab42
  3. knn helper · level 1 · ran · 86fd210ea5960f23

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 3 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DGCNN_cls entry · level 1 · ran · deae149da586b0cb
  2. get_graph_feature helper · level 0 · unverified · 9019aa1bd21a7d63
  3. knn helper · level 1 · ran; the contract check could not run · cdd0141594039dcb

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DGCNN entry · level 1 · ran · 105ce77f02aa8fc3
  2. get_graph_feature helper · level 1 · ran; the contract check could not run (RAISES) · 9a8756778dd8234a
  3. knn helper · level 1 · ran; the contract check could not run · cdd0141594039dcb

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DGCNN entry · level 1 · ran · f746806bd48762f6
  2. get_graph_feature helper · level 1 · ran · our draft was wrong · 26b869462d7d37e6
  3. knn helper · level 1 · ran; the contract check could not run (RAISES) · ee7b4d081c1fd7b3

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. DGCNN entry · level 1 · ran · 5225ebf366dff39c
  2. get_graph_feature helper · level 1 · ran · our draft was wrong · ffacb4286b9c5b79
  3. knn helper · level 1 · ran; the contract check could not run (RAISES) · 999b1b3194e7ace2

harvested Assembly for Edge-Conv (graph method: Edge-Conv). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. get_edge_feature entry · level 0 · unverified · afb21d6165856bb0

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="1801.07829") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Part Segmentation3D Point Cloud Classification3D Semantic SegmentationFew-Shot 3D Point Cloud ClassificationPoint Cloud ClassificationPoint Cloud SegmentationSemantic SegmentationSupervised Only 3D Point Cloud Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part DGCNN Instance Average IoU 85.2 #51 of 67 Archive leaderboard report
3D Point Cloud Classification IntrA DGCNN F1 score (5-fold) 0.738 #11 of 12 Archive leaderboard report
3D Point Cloud Classification ModelNet40 DGCNN Mean Accuracy 90.2 #78 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 DGCNN Number of params 1.81M #78 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 DGCNN Overall Accuracy 92.9 #78 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40-C DGCNN Error Rate 0.259 #10 of 13 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN DGCNN Mean Accuracy 73.6 #73 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN DGCNN OBJ-BG (OA) 82.8 #73 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN DGCNN OBJ-ONLY (OA) 86.2 #73 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN DGCNN Overall Accuracy 78.1 #73 of 77 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) DGCNN Overall Accuracy 19.85 #31 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) DGCNN Standard Deviation 6.5 #31 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) DGCNN Overall Accuracy 16.9 #31 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) DGCNN Standard Deviation 1.5 #31 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) DGCNN Overall Accuracy 31.6 #30 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) DGCNN Standard Deviation 9.0 #30 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) DGCNN Overall Accuracy 40.8 #30 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) DGCNN Standard Deviation 14.6 #30 of 30 Archive leaderboard report
Point Cloud Classification PointCloud-C DGCNN mean Corruption Error (mCE) 1.000 #17 of 24 Archive leaderboard report
Point Cloud Segmentation PointCloud-C DGCNN mean Corruption Error (mCE) 1.000 #6 of 11 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN DGCNN GFLOPs 2.4 #9 of 12 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN DGCNN Number of params (M) 1.8 #9 of 12 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN DGCNN Overall Accuracy (PB_T50_RS) 78.1 #9 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