Research map / Point clouds / Segmentation and detection
SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
Xinge Zhu Yuexin Ma Tai Wang Yan Xu Jianping Shi Dahua Lin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add shape-aware grouping heads (ablation) | PointPillar · nuScenes val | mAP: 29.4 -> 40.6 | Improved |
| add shape-aware grouping heads (ablation) | PointPillar · nuScenes val | NDS: 44.9 -> 51.3 | Improved |
| add shape signature objective on top of grouping heads (ablation) | PointPillar · nuScenes val | mAP: 40.6 -> 45.3 | Improved |
| add shape signature objective on top of grouping heads (ablation) | PointPillar · nuScenes val | NDS: 51.3 -> 57.0 | Improved |
| add shape signature objective (ablation) | PointPillar · nuScenes val | mAP: 29.4 -> 36.6 | Improved |
| add shape signature objective (ablation) | Second · nuScenes val | mAP: 31.1 -> 34.3 | Improved |
| add shape signature objective (ablation) | PointPillar · Lyft public test | mAP-3D: 13.4 -> 16.2 | Improved |
| add shape signature objective (ablation) | Second · Lyft public test | mAP-3D: 13.0 -> 15.4 | Improved |
| add shape signature objective (ablation) | PointPillar · KITTI car (moderate, IoU 0.7) | mAP: 74.3 -> 76.2 | Improved |
| add shape signature objective (ablation) | PointPillar · KITTI pedestrian (moderate, IoU 0.7) | mAP: 41.9 -> 43.5 | Improved |
| use shape-aware grouping heads instead of one-to-one heads (ablation) | PointPillar · nuScenes val | mAP: 32.0 -> 39.1 | Improved |
| use shape signature instead of implicit shape signature (ablation) | PointPillar · nuScenes val | mAP: 31.4 -> 36.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PointPillars — PointPillars: Fast Encoders for Object Detection From Point Clouds (CVPR 2019) · better on 2 of 2 shared results
- Voxelnet — VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (CVPR 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Group-Free 3D Object Detection via Transformers (ICCV 2021 · similarity 0.86)
- Shape-Oriented Convolution Neural Network for Point Cloud Analysis (AAAI 2020 · similarity 0.86)
- A Hierarchical Graph Network for 3D Object Detection on Point Clouds (CVPR 2020 · similarity 0.85)
- Geometry-Aware 3D Salient Object Detection Network (AAAI 2025 · similarity 0.84)
- LION: Linear Group RNN for 3D Object Detection in Point Clouds (NeurIPS 2024 · similarity 0.84)
- SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
