Papers › Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis

Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis

9 Oct 2022arXiv:2210.04208archive 2025-07-28

Xu Yan, Heshen Zhan, Chaoda Zheng, Jiantao Gao, Ruimao Zhang, Shuguang Cui, Zhen Li

Although recent point cloud analysis achieves impressive progress, the paradigm of representation learning from a single modality gradually meets its bottleneck. In this work, we take a step towards more discriminative 3D point cloud representation by fully taking advantages of images which inherently contain richer appearance information, e.g., texture, color, and shade. Specifically, this paper introduces a simple but effective point cloud cross-modality training (PointCMT) strategy, which utilizes view-images, i.e., rendered or projected 2D images of the 3D object, to boost point cloud analysis. In practice, to effectively acquire auxiliary knowledge from view images, we develop a teacher-student framework and formulate the cross modal learning as a knowledge distillation problem. PointCMT eliminates the distribution discrepancy between different modalities through novel feature and classifier enhancement criteria and avoids potential negative transfer effectively. Note that PointCMT effectively improves the point-only representation without architecture modification. Sufficient experiments verify significant gains on various datasets using appealing backbones, i.e., equipped with PointCMT, PointNet++ and PointMLP achieve state-of-the-art performance on two benchmarks, i.e., 94.4% and 86.7% accuracy on ModelNet40 and ScanObjectNN, respectively. Code will be made available at https://github.com/ZhanHeshen/PointCMT.

PaperPDFCode

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

Code

zhanheshen/pointcmt officialmentioned in papermentioned on GitHubpytorch report
yanx27/2dpass 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

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

Tasks

3D Point Cloud ClassificationKnowledge DistillationRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ModelNet40 PointNet2+PointCMT Mean Accuracy 91.2 #14 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointNet2+PointCMT Number of params 1.62M #14 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointNet2+PointCMT Overall Accuracy 94.4 #14 of 111 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointCMT Mean Accuracy 84.8 #46 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointCMT Number of params 12.6M #46 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointCMT Overall Accuracy 86.7 #46 of 77 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

Knowledge Distillation

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