Papers › Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point...

Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation

20 Sep 2022arXiv:2209.09483archive 2025-07-28

Haoyi Xiu, Xin Liu, Weimin WANG, Kyoung-Sook Kim, Takayuki Shinohara, Qiong Chang, Masashi Matsuoka

3D point clouds are discrete samples of continuous surfaces which can be used for various applications. However, the lack of true connectivity information, i.e., edge information, makes point cloud recognition challenging. Recent edge-aware methods incorporate edge modeling into network designs to better describe local structures. Although these methods show that incorporating edge information is beneficial, how edge information helps remains unclear, making it difficult for users to analyze its usefulness. To shed light on this issue, in this study, we propose a new algorithm called Diffusion Unit (DU) that handles edge information in a principled and interpretable manner while providing decent improvement. First, we theoretically show that DU learns to perform task-beneficial edge enhancement and suppression. Second, we experimentally observe and verify the edge enhancement and suppression behavior. Third, we empirically demonstrate that this behavior contributes to performance improvement. Extensive experiments and analyses performed on challenging benchmarks verify the effectiveness of DU. Specifically, our method achieves state-of-the-art performance in object part segmentation using ShapeNet part and scene segmentation using S3DIS. Our source code is available at https://github.com/martianxiu/DiffusionUnit.

PaperPDFCode

Code

martianxiu/diffusionunit officialmentioned in papermentioned on GitHubpytorch 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 Part SegmentationPoint Cloud SegmentationScene SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part Diffusion Unit Class Average IoU 85.2 #6 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part Diffusion Unit Instance Average IoU 87.1 #6 of 67 Archive leaderboard report
Semantic Segmentation S3DIS Area5 Diffusion Unit Number of params 8.1M #22 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 Diffusion Unit mAcc 78.1 #22 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 Diffusion Unit mIoU 72.2 #22 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 Diffusion Unit oAcc 91.3 #22 of 61 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

Diffusion

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