Research map / Point clouds / Segmentation and detection
RBGNet: Ray-Based Grouping for 3D Object Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 ray-based feature grouping with 66 rays (ablation) | VoteNet baseline on ScanNet V2 · ScanNet V2 | mAP@0.25: 66.2 -> 69.0 | Helped |
| Add ray-based feature grouping with 66 rays (ablation) | VoteNet baseline on ScanNet V2 · ScanNet V2 | mAP@0.5: 48.2 -> 52.9 | Helped |
| Add foreground biased sampling (ablation) | VoteNet baseline on ScanNet V2 · ScanNet V2 | mAP@0.25: 66.2 -> 67.1 | Helped |
| Add foreground biased sampling (ablation) | VoteNet baseline on ScanNet V2 · ScanNet V2 | mAP@0.5: 48.2 -> 49.0 | Helped |
| Use 102 rays instead of 66 (ablation) | RBGNet on ScanNet V2 · ScanNet V2 | mAP@0.25: 69.6 -> 69.9 | Helped |
| Use 102 rays instead of 66 (ablation) | RBGNet on ScanNet V2 · ScanNet V2 | mAP@0.5: 53.6 -> 53.9 | Helped |
| Replace ray point classification with ray length regression (ablation) | RBGNet (66 rays) on ScanNet V2 · ScanNet V2 | mAP@0.25: 69.6 -> 68.0 | Hurt |
| Replace ray point classification with ray length regression (ablation) | RBGNet (66 rays) on ScanNet V2 · ScanNet V2 | mAP@0.5: 53.6 -> 50.2 | Hurt |
| Use 102 instead of 66 rays (ablation) | RBGNet on ScanNet V2 · ScanNet V2 | frames/s: 4.75 (66 rays) -> not reported for 102 rays | Mixed |
Closest papers by meaning
- ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes (CVPR 2020 · similarity 0.87)
- SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection (AAAI 2024 · similarity 0.87)
- Cubify Anything: Scaling Indoor 3D Object Detection (CVPR 2025 · similarity 0.86)
- LION: Linear Group RNN for 3D Object Detection in Point Clouds (NeurIPS 2024 · similarity 0.86)
- UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes (NeurIPS 2024 · similarity 0.85)
- MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweeps (NeurIPS 2024 · similarity 0.85)
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.