Papers › Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework

Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework

15 Feb 2022ICLR 2022 4arXiv:2202.07123archive 2025-07-28

Xu Ma, Can Qin, Haoxuan You, Haoxi Ran, Yun Fu

Point cloud analysis is challenging due to irregularity and unordered data structure. To capture the 3D geometries, prior works mainly rely on exploring sophisticated local geometric extractors using convolution, graph, or attention mechanisms. These methods, however, incur unfavorable latency during inference, and the performance saturates over the past few years. In this paper, we present a novel perspective on this task. We notice that detailed local geometrical information probably is not the key to point cloud analysis -- we introduce a pure residual MLP network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively. Equipped with a proposed lightweight geometric affine module, PointMLP delivers the new state-of-the-art on multiple datasets. On the real-world ScanObjectNN dataset, our method even surpasses the prior best method by 3.3% accuracy. We emphasize that PointMLP achieves this strong performance without any sophisticated operations, hence leading to a superior inference speed. Compared to most recent CurveNet, PointMLP trains 2x faster, tests 7x faster, and is more accurate on ModelNet40 benchmark. We hope our PointMLP may help the community towards a better understanding of point cloud analysis. The code is available at https://github.com/ma-xu/pointMLP-pytorch.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology 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="2202.07123")

Code

Syntology Ran 10 of 10 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 3 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 8 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ma-xu/pointmlp-pytorch officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

10 samples harvested; 10 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
3ran · fixture could not drive it
6ran

Licence: 2 of the 10 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 ma-xu/pointmlp-pytorch. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

ConvBNReLU1D ma-xu/pointmlp-pytorch/classification_ModelNet40/models/pointmlp.py official repository ran fingerprinted Apache-2.0 (permissive) · 26a19f56c677c289 · report
ConvBNReLURes1D ma-xu/pointmlp-pytorch/classification_ModelNet40/models/pointmlp.py official repository ran Apache-2.0 (permissive) · 4016e6fe8b4197d0 · report
LocalGrouper ma-xu/pointmlp-pytorch/classification_ModelNet40/models/pointmlp.py official repository ran Apache-2.0 (permissive) · a59e49e189815469 · report
Model ma-xu/pointmlp-pytorch/classification_ModelNet40/models/pointmlp.py official repository ran Apache-2.0 (permissive) · c1bbda9d8854e8d6 · report
PosExtraction ma-xu/pointmlp-pytorch/classification_ModelNet40/models/pointmlp.py official repository ran fingerprinted Apache-2.0 (permissive) · 01c6204da6d2e1e3 · report
PreExtraction ma-xu/pointmlp-pytorch/classification_ModelNet40/models/pointmlp.py official repository ran Apache-2.0 (permissive) · 87c2190f708f0959 · report
get_activation ma-xu/pointmlp-pytorch/classification_ModelNet40/models/pointmlp.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 194020d4610c8bad · report
knn_point ma-xu/pointmlp-pytorch/classification_ModelNet40/models/pointmlp.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 3fc6f6b239b211f9 · report
index_points identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · 449a0265144f6530 · report
square_distance identical code first harvested elsewhere ran · fixture could not drive it fingerprinted licence of this copy not recorded · 3bfe172e686075cd · report

Tasks

3D Point Cloud ClassificationPoint Cloud SegmentationSupervised Only 3D Point Cloud Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ModelNet40 PointMLP Mean Accuracy 91.4 #11 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointMLP Overall Accuracy 94.5 #11 of 111 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointMLP Mean Accuracy 84.4 #53 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointMLP Overall Accuracy 85.7 #53 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointMLP-elite Mean Accuracy 81.8 #60 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointMLP-elite Overall Accuracy 83.8 #60 of 77 Archive leaderboard report
Point Cloud Segmentation PointCloud-C PointMLP mean Corruption Error (mCE) 0.977 #4 of 11 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN PointMLP GFLOPs 31.4 #8 of 12 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN PointMLP Number of params (M) 12.6 #8 of 12 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN PointMLP Overall Accuracy (PB_T50_RS) 85.4 #8 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