Papers › SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds

SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds

1 Aug 2020ECCV 2020 8archive 2025-07-28

Xinge Zhu      Yuexin Ma      Tai Wang      Yan Xu Jianping Shi      Dahua Lin

Multi-class 3D object detection aims to classify and localize objects of multiple categories from point clouds. Due to the nature of point clouds, i.e. unstructured, sparse and noisy, some features benefit-ting multi-class discrimination are underexploited, such as shape information. In this paper, we propose a novel 3D shape signature to explore the shape information from point clouds. By incorporating operations of symmetry, convex hull and chebyshev fitting, the proposed shape sig-nature is not only compact and effective but also robust to the noise, which serves as a soft constraint to improve the feature capability of multi-class discrimination. Based on the proposed shape signature, we develop the shape signature networks (SSN) for 3D object detection, which consist of pyramid feature encoding part, shape-aware grouping heads and explicit shape encoding objective. Experiments show that the proposed method performs remarkably better than existing methods on two large-scale datasets. Furthermore, our shape signature could act as a plug-and-play component and ablation study shows its effectiveness and good scalability

PaperPDFCode

Code

xinge008/SSN officialmentioned in paperpytorch 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 Object DetectionObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection nuScenes SSN NDS 0.62 #160 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN mAAE 0.09 #160 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN mAOE 0.43 #160 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN mAP 0.51 #160 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN mASE 0.24 #160 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN mATE 0.34 #160 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN mAVE 0.27 #160 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN-v1 NDS 0.57 #227 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN-v1 mAAE 0.31 #227 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN-v1 mAOE 0.43 #227 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN-v1 mAP 0.46 #227 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN-v1 mASE 0.26 #227 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN-v1 mATE 0.37 #227 of 372 Archive leaderboard report
3D Object Detection nuScenes SSN-v1 mAVE 0.26 #227 of 372 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