Papers › Benchmarking and Analyzing Point Cloud Classification under Corruptions

Benchmarking and Analyzing Point Cloud Classification under Corruptions

7 Feb 2022arXiv:2202.03377archive 2025-07-28

Jiawei Ren, Liang Pan, Ziwei Liu

3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision. In this work, we aim to rigorously benchmark and analyze point cloud classification under corruptions. To conduct a systematic investigation, we first provide a taxonomy of common 3D corruptions and identify the atomic corruptions. Then, we perform a comprehensive evaluation on a wide range of representative point cloud models to understand their robustness and generalizability. Our benchmark results show that although point cloud classification performance improves over time, the state-of-the-art methods are on the verge of being less robust. Based on the obtained observations, we propose several effective techniques to enhance point cloud classifier robustness. We hope our comprehensive benchmark, in-depth analysis, and proposed techniques could spark future research in robust 3D perception.

PaperPDFCodeCode 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 13 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 11 ran (6 with no instrument failure; 5 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.

jiawei-ren/modelnetc officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 13 samples, 11 ran (5 instrument-failed) · 2 unverified report
ldkong1205/PointCloud-C mentioned on GitHubpytorchSyntology: 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

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

13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 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.

1ran · our draft was wrong
4ran; the contract check could not run
6ran
2unverified

Licence: 2 of the 13 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 jiawei-ren/modelnetc. “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.

jiawei-ren/modelnetc official repository 13 samples, 11 ran (5 instrument-failed) · 2 unverified
corrupt_jitter build_modelnetc/corrupt_utils.py ran fingerprinted Apache-2.0 (permissive) · b5dd3f043c271b69 · report fixture: signature pointcloud:ndarray/2/float, level:int/0/int · returned ndarray · level recorded 2026-09-24
corrupt_rotate build_modelnetc/corrupt_utils.py ran fingerprinted Apache-2.0 (permissive) · a260494677ed35d8 · report fixture: signature pointcloud:ndarray/2/float, level:int/0/int · returned ndarray · level recorded 2026-09-24
corrupt_scale build_modelnetc/corrupt_utils.py ran fingerprinted Apache-2.0 (permissive) · 8f0a929253e9f007 · report fixture: signature pointcloud:ndarray/2/float, level:int/0/int · returned ndarray · level recorded 2026-09-24
cut_points GDANet/rsmix_provider.py ran Apache-2.0 (permissive) · d26265da343f8191 · report fixture: signature data_batch:ndarray/3/float, idx:ndarray/2/int, radius:float/0/float, nsample:int/0/int · returned tuple · level recorded 2026-09-24
cut_points_knn GDANet/rsmix_provider.py ran Apache-2.0 (permissive) · f3bf3d79146b55df · report fixture: signature data_batch:ndarray/3/float, idx:ndarray/2/int, radius:float/0/float, nsample:int/0/int, k:int/0/int · returned tuple · level recorded 2026-09-24
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
PointWOLF/model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 9a8756778dd8234a · report fixture: 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
PointWOLF/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · cdd0141594039dcb · report fixture: signature x:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-22
load_h5 in 10 papers modelnetc_utils/modelnetc_utils/dataset.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 1bfbbe6bae6f8e29 · report fixture: signature h5_name:str/0/str · returned tuple · level recorded 2026-09-24
rotate_point_cloud in 17 papers GDANet/provider.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · adb85367d5bf360a · report fixture: signature batch_data:ndarray/3/float · returned ndarray · level recorded 2026-09-22
shuffle_data in 34 papers GDANet/provider.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 06353aadebc1724b · report fixture: signature data:ndarray/3/float, labels:ndarray/1/int · returned tuple · level recorded 2026-09-24
shuffle_points in 13 papers GDANet/provider.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · a97f76b9c0811c93 · report fixture: signature batch_data:ndarray/3/float · returned ndarray · level recorded 2026-09-22
knn_points GDANet/rsmix_provider.py unverified Apache-2.0 (permissive) · a7032e8191925cc0 · report
load_data in 700 papers build_modelnetc/corrupt.py unverified Apache-2.0 (permissive) · 6002e0aaef533772 · report

Tasks

BenchmarkingClassificationPoint Cloud Classification

Datasets

Introduced by this paper, per the archive.

PointCloud-C

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Cloud Classification PointCloud-C WOLFMix (GDANet) mean Corruption Error (mCE) 0.571 #8 of 24 Archive leaderboard report
Point Cloud Classification PointCloud-C WOLFMix (DGCNN) mean Corruption Error (mCE) 0.590 #9 of 24 Archive leaderboard report
Point Cloud Classification PointCloud-C WOLFMix (RPC) mean Corruption Error (mCE) 0.601 #10 of 24 Archive leaderboard report
Point Cloud Classification PointCloud-C RPC mean Corruption Error (mCE) 0.863 #13 of 24 Archive leaderboard report
Point Cloud Classification PointCloud-C WOLFMix (PointNet) mean Corruption Error (mCE) 1.180 #23 of 24 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