Research map / Point clouds / Point cloud classification
PTTR: Relational 3D Point Cloud Object Tracking With Transformer
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 |
|---|---|---|---|
| use PTTR instead of LTTR | 3D single-object tracking · KITTI tracking test, average | Success: 50.0 -> 58.4 | Helped |
| use PTTR instead of LTTR | 3D single-object tracking · KITTI tracking test, average | Precision: 67.4 -> 77.8 | Helped |
| use PTTR instead of P2B | 3D single-object tracking · Waymo SOT test, average | Success: 40.6 -> 50.3 | Helped |
| use PTTR instead of P2B | 3D single-object tracking · Waymo SOT test, average | Precision: 53.9 -> 64.9 | Helped |
| add relation-aware sampling instead of random sampling (ablation) | PTTR · KITTI tracking test, average | Success: 52.9 -> 58.4 | Helped |
| add relation-aware sampling instead of D-FPS (ablation) | PTTR · KITTI tracking test, average | Success: 51.4 -> 58.4 | Helped |
| add relation-aware sampling instead of F-FPS (ablation) | PTTR · KITTI tracking test, average | Success: 54.3 -> 58.4 | Helped |
| add PRT and PRM (ablation) | PTTR · KITTI tracking test, average | Success: 29.8 -> 58.4 | Helped |
| add PRM (ablation) | PTTR with PRT · KITTI tracking test, average | Success: 56.7 -> 58.4 | Helped |
| use PRT rather than cosine similarity (ablation) | PTTR · KITTI tracking test, average | Success: 50.5 -> 58.4 | Helped |
| add offset attention and feature normalization (ablation) | PTTR Relation Attention · KITTI tracking test, average | Success: 45.6 -> 58.4 | Helped |
| add feature normalization (ablation) | PTTR Relation Attention with offset attention · KITTI tracking test, average | Success: 52.2 -> 58.4 | Helped |
Closest papers by meaning
- Point Transformer V3: Simpler Faster Stronger (CVPR 2024 · similarity 0.89)
- M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking (AAAI 2024 · similarity 0.88)
- Towards Category Unification of 3D Single Object Tracking on Point Clouds (ICLR 2024 · similarity 0.88)
- PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection (CVPR 2024 · similarity 0.87)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.87)
- Scene Flow Prior Based Point Cloud Completion with Masked Transformer (Student Abstract) (AAAI 2024 · similarity 0.86)
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.