Papers › Surface Representation for Point Clouds

Surface Representation for Point Clouds

11 May 2022CVPR 2022 1arXiv:2205.05740archive 2025-07-28

Haoxi Ran, Jun Liu, Chengjie Wang

Most prior work represents the shapes of point clouds by coordinates. However, it is insufficient to describe the local geometry directly. In this paper, we present RepSurf (representative surfaces), a novel representation of point clouds to explicitly depict the very local structure. We explore two variants of RepSurf, Triangular RepSurf and Umbrella RepSurf inspired by triangle meshes and umbrella curvature in computer graphics. We compute the representations of RepSurf by predefined geometric priors after surface reconstruction. RepSurf can be a plug-and-play module for most point cloud models thanks to its free collaboration with irregular points. Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency. With an increase of around 0.008M number of parameters, 0.04G FLOPs, and 1.12ms inference time, our method achieves 94.7% (+0.5%) on ModelNet40, and 84.6% (+1.8%) on ScanObjectNN for classification, while 74.3% (+0.8%) mIoU on S3DIS 6-fold, and 70.0% (+1.6%) mIoU on ScanNet for segmentation. For detection, previous state-of-the-art detector with our RepSurf obtains 71.2% (+2.1%) mAP₂₅, 54.8% (+2.0%) mAP₅₀ on ScanNetV2, and 64.9% (+1.9%) mAP₂₅, 47.7% (+2.5%) mAP₅₀ on SUN RGB-D. Our lightweight Triangular RepSurf performs its excellence on these benchmarks as well. The code is publicly available at https://github.com/hancyran/RepSurf.

PaperPDFConference PDFCodeCode Syntology ran

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 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (11 with no instrument failure; 2 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.

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

hancyran/RepSurf officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 13 ran (2 instrument-failed) · 2 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.

Code Syntology ran Syntology

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 2 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.

2ran · our draft was wrong
11ran
2unverified

Licence: 2 of the 15 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 hancyran/RepSurf. “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”. “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.

hancyran/RepSurf official repository 15 samples, 13 ran (2 instrument-failed) · 2 unverified
cal_normal classification/modules/recons_utils.py ran Apache-2.0 (permissive) · 90abbae1e8a9515c · report fixture: signature group_xyz:Tensor/4/float, random_inv:bool/0/bool, is_group:bool/0/bool · returned Tensor · level recorded 2026-09-24
farthest_point_sample in 64 papers classification/modules/pointnet2_utils.py ran Apache-2.0 (permissive) · e165142db58e96b5 · report fixture: signature xyz:Tensor/3/float, npoint:int/0/int, cuda:bool/0/bool · returned Tensor · level recorded 2026-09-24
get_aug_args classification/modules/ptaug_utils.py ran Apache-2.0 (permissive) · b6178ce69e144ce7 · report fixture: signature args:Args/0/? · returned dict · level recorded 2026-09-24
index_points in 49 papers classification/modules/pointnet2_utils.py ran Apache-2.0 (permissive) · 25dec942fa25547e · report fixture: signature points:Tensor/3/float, idx:Tensor/2/int, cuda:bool/0/bool, is_group:bool/0/bool · returned Tensor · level recorded 2026-09-24
pca in 16 papers classification/modules/recons_utils.py ran Apache-2.0 (permissive) · 43f6d0436aebc666 · report fixture: signature X:Tensor/2/float, k:int/0/int, center:bool/0/bool · returned dict · level recorded 2026-09-24
resort_points classification/modules/repsurface_utils.py ran Apache-2.0 (permissive) · ef36d757b28c9f41 · report fixture: signature points:Tensor/4/float, idx:Tensor/3/int · returned Tensor · level recorded 2026-09-24
shift_point_cloud classification/modules/ptaug_utils.py ran fingerprinted Apache-2.0 (permissive) · cf984792acb072ff · report fixture: signature batch_data:Tensor/3/float, shift_range:float/0/float · returned Tensor · level recorded 2026-09-24
square_distance in 89 papers
census: 11 implementations from 18 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
classification/modules/pointnet2_utils.py ran fingerprinted Apache-2.0 (permissive) · 9d026e3279fe6446 · report fixture: signature src:Tensor/3/float, dst:Tensor/3/float · returned Tensor · level recorded 2026-09-24
transform_point_cloud in 6 papers classification/modules/ptaug_utils.py ran Apache-2.0 (permissive) · 8a2b98e6b1b0965e · report fixture: signature batch:Tensor/3/float, args:Args/0/?, aug_args:dict/0/?, train:bool/0/bool, label:Tensor/1/int · returned tuple · level recorded 2026-09-24
xyz2cylind segmentation/modules/polar_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · bdaeeb5851d70f67 · report fixture: signature xyz:Tensor/2/float, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-24
xyz2cylind classification/modules/polar_utils.py ran fingerprinted Apache-2.0 (permissive) · ab4a32fde08cd85f · report fixture: signature xyz:Tensor/3/float, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-24
xyz2sphere segmentation/modules/polar_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · bcf83718dbe85554 · report fixture: signature xyz:Tensor/2/float, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-24
xyz2sphere classification/modules/polar_utils.py ran fingerprinted Apache-2.0 (permissive) · c5f00144812c665a · report fixture: signature xyz:Tensor/3/float, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-24
transform_point_cloud_coord segmentation/modules/aug_utils.py unverified Apache-2.0 (permissive) · 6b78fa00ee2dcd42 · report
transform_point_cloud_rgb segmentation/modules/aug_utils.py unverified Apache-2.0 (permissive) · 1794cefb931feef6 · report

Tasks

3D Object Detection3D Point Cloud Classification3D Semantic SegmentationSemantic SegmentationSupervised Only 3D Point Cloud ClassificationSurface Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection SUN-RGBD val RepSurf-U mAP@0.25 64.9 #13 of 32 Archive leaderboard report
3D Object Detection SUN-RGBD val RepSurf-U mAP@0.5 47.7 #13 of 32 Archive leaderboard report
3D Object Detection ScanNetV2 RepSurf-U mAP@0.25 71.2 #18 of 33 Archive leaderboard report
3D Object Detection ScanNetV2 RepSurf-U mAP@0.5 54.8 #18 of 33 Archive leaderboard report
3D Point Cloud Classification ModelNet40 RepSurf-U FLOPs 0.81G #9 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 RepSurf-U Number of params 1.48M #9 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 RepSurf-U Overall Accuracy 94.7 #9 of 111 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN RepSurf-U (2x) FLOPs 2.43G #52 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN RepSurf-U (2x) Number of params 6.80M #52 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN RepSurf-U (2x) Overall Accuracy 86.0 #52 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN RepSurf-U FLOPs 0.81G #58 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN RepSurf-U Number of params 1.48M #58 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN RepSurf-U Overall Accuracy 84.6 #58 of 77 Archive leaderboard report
Semantic Segmentation S3DIS RepSurf-U FLOPs 1.04G #14 of 54 Archive leaderboard report
Semantic Segmentation S3DIS RepSurf-U Mean IoU 74.3 #14 of 54 Archive leaderboard report
Semantic Segmentation S3DIS RepSurf-U Number of params 0.97M #14 of 54 Archive leaderboard report
Semantic Segmentation S3DIS RepSurf-U Params (M) 0.97 #14 of 54 Archive leaderboard report
Semantic Segmentation S3DIS RepSurf-U mAcc 82.6 #14 of 54 Archive leaderboard report
Semantic Segmentation S3DIS RepSurf-U oAcc 90.8 #14 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 RepSurf-U FLOPs 1.04G #36 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 RepSurf-U Number of params 0.97M #36 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 RepSurf-U mAcc 76.0 #36 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 RepSurf-U mIoU 68.9 #36 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 RepSurf-U oAcc 90.2 #36 of 61 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