Papers › PointCNN: Convolution On 𝒳-Transformed Points

PointCNN: Convolution On 𝒳-Transformed Points

23 Jan 2018NeurIPS 2018arXiv:1801.07791archive 2025-07-28

Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen

We present a simple and general framework for feature learning from point clouds. The key to the success of CNNs is the convolution operator that is capable of leveraging spatially-local correlation in data represented densely in grids (e.g. images). However, point clouds are irregular and unordered, thus directly convolving kernels against features associated with the points, will result in desertion of shape information and variance to point ordering. To address these problems, we propose to learn an 𝒳-transformation from the input points, to simultaneously promote two causes. The first is the weighting of the input features associated with the points, and the second is the permutation of the points into a latent and potentially canonical order. Element-wise product and sum operations of the typical convolution operator are subsequently applied on the 𝒳-transformed features. The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN. Experiments show that PointCNN achieves on par or better performance than state-of-the-art methods on multiple challenging benchmark datasets and tasks.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

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

yangyanli/PointCNN officialmentioned in papermentioned on GitHubtfNOASSERTIONSyntology: not harvested report
LebronGG/PointCnn mentioned on GitHubtfSyntology: not harvested report
Lw510107/PointCNN mentioned on GitHubtfSyntology: not harvested report
agarret7/PointCNN mentioned on GitHubpytorchSyntology: not harvested report
c3210927/point_cnn mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
chinakook/PointCNN.MX mentioned on GitHubtfSyntology: not harvested report
dream-chaser/pointcnn_for_3DFER mentioned on GitHubtfSyntology: not harvested report
hxdengBerkeley/PointCNN.Pytorch mentioned on GitHubtfSyntology: not harvested report
lanlan96/3drm mentioned on GitHubpytorchSyntology: not harvested report
luost26/diffusion-point-cloud mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Diffusion Probabilistic Models for 3D Point Cloud Generation (arXiv:2103.01458; that paper's own run record: 22 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
nicolas-chaulet/torch-points3d mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
octree-nn/ocnn-pytorch mentioned on GitHubpytorchSyntology: not harvested report
pyg-team/pytorch_geometric mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning the Geometry of Data: A Mathematical Review of Shape Space Analysis (arXiv:2606.17022; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
tch/pointcnn mentioned on GitHubtfSyntology: not harvested report
tschattschneider/pointcnn mentioned on GitHubtfSyntology: not harvested report
NMADALI97/PointCNN_Pytorch pytorchSyntology: not harvested 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Instance Segmentation3D Part Segmentation3D Point Cloud ClassificationFew-Shot 3D Point Cloud Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Instance Segmentation S3DIS PointCNN mAcc 75.61 #21 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS PointCNN mIoU 65.39% #21 of 21 Archive leaderboard report
3D Part Segmentation IntrA PointCNN DSC (A) 81.74 #4 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointCNN DSC (V) 96.62 #4 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointCNN IoU (A) 74.11 #4 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointCNN IoU (V) 93.59 #4 of 7 Archive leaderboard report
3D Part Segmentation ShapeNet-Part PointCNN Class Average IoU 84.6 #35 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part PointCNN Instance Average IoU 86.14 #35 of 67 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointCNN Mean Accuracy 75.1 #72 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointCNN OBJ-BG (OA) 86.1 #72 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointCNN OBJ-ONLY (OA) 85.5 #72 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointCNN Overall Accuracy 78.5 #72 of 77 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) PointCNN Overall Accuracy 65.41 #25 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) PointCNN Standard Deviation 8.9 #25 of 30 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

Convolution

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