Research map / Point clouds / Segmentation and detection
Group-Free 3D Object Detection via Transformers
Ze Liu, Zheng Zhang, Yue Cao, Han Hu, Xin Tong
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 |
|---|---|---|---|
| use KPS sampling instead of FPS for initial candidates (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25 / mAP@0.5: 64.5 -> 66.3 mAP@0.25, 46.2 -> 48.5 mAP@0.5 | Improved |
| add NMS to KPS sampling (KPS-NMS) (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25 / mAP@0.5: 66.3 -> 65.8 mAP@0.25, 48.5 -> 48.7 mAP@0.5 | No clear effect |
| vary k in KPS sampling (1, 2, 4, 6) (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25: 65.7, 65.8, 66.3, 66.1 mAP@0.25 | No clear effect |
| add iterative spatial-encoding refinement of box location (center+size) (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.5: 43.4 -> 48.5 mAP@0.5, 64.7 -> 66.3 mAP@0.25 | Improved |
| add fixed position encoding without iterative refinement (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25 / mAP@0.5: 64.7 -> 64.6 mAP@0.25, 43.4 -> 43.5 mAP@0.5 | No clear effect |
| encode box size in addition to box center in spatial encoding (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25 / mAP@0.5: 65.2 -> 66.3 mAP@0.25, 47.5 -> 48.5 mAP@0.5 | Improved |
| add 6 attention decoder layers (vs 0 layers) (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25 / mAP@0.5: 63.3 -> 66.3 mAP@0.25, 40.7 -> 48.5 mAP@0.5 | Improved |
| add multi-stage ensemble of predictions (ablation) | Group-Free 3D · SUN RGB-D | mAP@0.25 / mAP@0.5: 59.2 -> 63.0 mAP@0.25, 43.3 -> 45.2 mAP@0.5 | Improved |
| add multi-stage ensemble of predictions (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25 / mAP@0.5: 66.3 -> 66.4 mAP@0.25, 48.5 -> 48.7 mAP@0.5 | No clear effect |
| use attention over all points instead of RoI-Pooling grouping (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25 / mAP@0.5: 65.1 -> 66.3 mAP@0.25, 44.4 -> 48.5 mAP@0.5 | Improved |
| use attention over all points instead of Voting grouping (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25 / mAP@0.5: 64.2 -> 66.3 mAP@0.25, 44.1 -> 48.5 mAP@0.5 | Improved |
| widen backbone 2x and use 12 decoder layers (vs 6 layers PointNet++) (ablation) | Group-Free 3D · ScanNet V2 | mAP@0.25 / mAP@0.5: 67.2 -> 68.8 mAP@0.25, 49.7 -> 52.1 mAP@0.5 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- 3D-MPA — 3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation (CVPR 2020) · better on 2 of 2 shared results
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
- CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds (NeurIPS 2022 · similarity 0.90)
- From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network (TPAMI 2020 · similarity 0.89)
- Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection From Point Clouds (TPAMI 2021 · similarity 0.89)
- Deep Hough Voting for 3D Object Detection in Point Clouds (ICCV 2019 · similarity 0.89)
- SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection (AAAI 2024 · similarity 0.89)
- LION: Linear Group RNN for 3D Object Detection in Point Clouds (NeurIPS 2024 · similarity 0.89)
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.
