Papers › Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions

Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions

28 Jan 2022arXiv:2201.12296archive 2025-07-28

Jiachen Sun, Qingzhao Zhang, Bhavya Kailkhura, Zhiding Yu, Chaowei Xiao, Z. Morley Mao

Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications. However, their robustness against corruptions is less studied. In this paper, we present ModelNet40-C, the first comprehensive benchmark on 3D point cloud corruption robustness, consisting of 15 common and realistic corruptions. Our evaluation shows a significant gap between the performances on ModelNet40 and ModelNet40-C for state-of-the-art (SOTA) models. To reduce the gap, we propose a simple but effective method by combining PointCutMix-R and TENT after evaluating a wide range of augmentation and test-time adaptation strategies. We identify a number of critical insights for future studies on corruption robustness in point cloud recognition. For instance, we unveil that Transformer-based architectures with proper training recipes achieve the strongest robustness. We hope our in-depth analysis will motivate the development of robust training strategies or architecture designs in the 3D point cloud domain. Our codebase and dataset are included in https://github.com/jiachens/ModelNet40-C

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2201.12296")

Code

Syntology Ran 20 of 29 code samples harvested from 3 repositories linked to this paper; 9 have no recorded run. Of those that ran: 2 ran · honoured contract; 3 ran · our draft was wrong; 5 ran · fixture could not drive it; 10 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 9 ran; community (archive-listed): 16 samples from 2 repositories, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jiachens/ModelNet40-C officialmentioned in papermentioned on GitHubpytorchBSD-3-Clause report
RF5/CurveNet mentioned on GitHubpytorch report
dogyoonlee/RSMix mentioned on GitHubtfMIT report
dogyoonlee/RSMix-official mentioned on GitHubtf report
hamidreza-dastmalchi/3dd-tta mentioned on GitHubpytorch report
tiangexiang/CurveNet mentioned on GitHubpytorchMIT 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

29 samples harvested; 20 ran; 2 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · honoured contract
3ran · our draft was wrong
5ran · fixture could not drive it
10ran
9unverified

Licence: 0 of the 29 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

index_points jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/models/pointmlp.py official repository ran · fixture could not drive it BSD-3-Clause (permissive) · 449a0265144f6530 · report
cal_loss jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/helper.py official repository ran · fixture could not drive it BSD-3-Clause (permissive) · c6c2758c0c2fa756 · report
format_time jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/utils/misc.py official repository ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 8d7ec010c29e813b · report
get_activation jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/models/pointmlp.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · 194020d4610c8bad · report
get_mean_and_std jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/utils/misc.py official repository ran BSD-3-Clause (permissive) · 2c92cec199cf12cd · report
load_data jiachens/ModelNet40-C/dataloader.py official repository ran BSD-3-Clause (permissive) · babac28fe6cf159e · report
plot_overlap jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/utils/logger.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · 50afa2863ffd9fde · report
smooth_loss jiachens/ModelNet40-C/all_utils.py official repository ran BSD-3-Clause (permissive) · f7ff7240ba3cadd3 · report
square_distance jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/models/pointmlp.py official repository ran · fixture could not drive it fingerprinted BSD-3-Clause (permissive) · 3bfe172e686075cd · report
load_data jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/data.py official repository unverified BSD-3-Clause (permissive) · 8281e96e1ddd5bf2 · report
random_point_dropout jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/data.py official repository unverified BSD-3-Clause (permissive) · 05a0f3632a145154 · report
rscnn_voting_evaluate_cls jiachens/ModelNet40-C/all_utils.py official repository unverified BSD-3-Clause (permissive) · 0cd52267ed0a888c · report
translate_pointcloud jiachens/ModelNet40-C/pointMLP/classification_ModelNet40/data.py official repository unverified BSD-3-Clause (permissive) · 791051c3e72b67d2 · report
calculate_shape_IoU tiangexiang/CurveNet/core/main_partseg.py community (archive-listed) ran MIT (permissive) · 2a3bec3110f3fc3c · report
farthest_point_sample dogyoonlee/RSMix/dgcnn_rsmix/ModelNetDataLoader.py community (archive-listed) ran fingerprinted MIT (permissive) · f80066a00e7156a2 · report
getDataFiles dogyoonlee/RSMix/pointnet2_rsmix/modelnet_h5_dataset.py community (archive-listed) ran MIT (permissive) · de3e0e22ff9c2e6a · report
get_graph_feature dogyoonlee/RSMix/dgcnn_rsmix/model.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 9a8756778dd8234a · report
gumbel_softmax tiangexiang/CurveNet/core/models/walk.py community (archive-listed) ran fingerprinted MIT (permissive) · 4483990ec7814fc4 · report
knn dogyoonlee/RSMix/dgcnn_rsmix/model.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · cdd0141594039dcb · report
knn tiangexiang/CurveNet/core/models/curvenet_util.py community (archive-listed) ran fingerprinted MIT (permissive) · fd43b3106ac73716 · report
normal_knn tiangexiang/CurveNet/core/models/curvenet_util.py community (archive-listed) ran fingerprinted MIT (permissive) · 1979f86a5b2b0446 · report
pc_normalize dogyoonlee/RSMix/dgcnn_rsmix/ModelNetDataLoader.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 4783fbece52f500e · report
pc_normalize dogyoonlee/RSMix/pointnet2_rsmix/modelnet_dataset.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · ec413739d406e611 · report
shuffle_data dogyoonlee/RSMix/pointnet2_rsmix/modelnet_h5_dataset.py community (archive-listed) ran MIT (permissive) · 06353aadebc1724b · report
batched_index_select tiangexiang/CurveNet/core/models/walk.py community (archive-listed) unverified MIT (permissive) · f091cdd21c103f22 · report
load_data_cls tiangexiang/CurveNet/core/data.py community (archive-listed) unverified MIT (permissive) · a228e71e16dc39c3 · report
load_data_normal tiangexiang/CurveNet/core/data.py community (archive-listed) unverified MIT (permissive) · 66aba4ffa53084a8 · report
load_data_partseg tiangexiang/CurveNet/core/data.py community (archive-listed) unverified MIT (permissive) · 1bfbd6440e25aa39 · report
load_h5 dogyoonlee/RSMix/pointnet2_rsmix/modelnet_h5_dataset.py community (archive-listed) unverified MIT (permissive) · 4378e52166c970f0 · report

Tasks

3D Point Cloud Classification3D Point Cloud Data AugmentationBenchmarkingTest-time Adaptation

Datasets

Introduced by this paper, per the archive.

ModelNet40-C

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ModelNet40-C PCT+PointCutMix-R Error Rate 0.163 #3 of 13 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDGCNNDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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