Research map / Point clouds / Point cloud classification
PointFlowNet: Learning Representations for Rigid Motion Estimation From Point Clouds
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 realistic Augmented KITTI examples to training (ablation) | PointFlowNet · Augmented KITTI validation | scene flow FG (m): 0.58 -> 0.28 | Helped |
| add realistic Augmented KITTI examples to training (ablation) | PointFlowNet · Augmented KITTI validation | scene flow All (m): 0.18 -> 0.16 | Helped |
| add realistic Augmented KITTI examples to training (ablation) | PointFlowNet · Augmented KITTI validation | object translation error (m): 0.57 -> 0.48 | Helped |
| add realistic Augmented KITTI examples to training (ablation) | PointFlowNet · KITTI validation | scene flow FG (m): 0.23 -> 0.18 | Helped |
| add realistic Augmented KITTI examples to training (ablation) | PointFlowNet · KITTI validation | scene flow All (m): 0.14 -> 0.14 | No clear effect |
| add realistic Augmented KITTI examples to training (ablation) | PointFlowNet · KITTI validation | object translation error (m): 0.30 -> 0.29 | Helped |
| estimate scene flow directly rather than deriving it from rigid-motion estimates | PointFlowNet · KITTI | scene flow accuracy | No clear effect |
| use PointFlowNet instead of Dewan et al.+Det. | scene-flow and object-motion estimation · KITTI test | scene flow All (m): 0.41 -> 0.16 | Helped |
| use PointFlowNet instead of Dewan et al.+Det. | scene-flow and object-motion estimation · KITTI test | object translation error (m): 0.55 -> 0.19 | Helped |
Closest papers by meaning
- FlowNet3D: Learning Scene Flow in 3D Point Clouds (CVPR 2019 · similarity 0.93)
- 3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling (CVPR 2024 · similarity 0.89)
- FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation (AAAI 2025 · similarity 0.89)
- ICP-Flow: LiDAR Scene Flow Estimation with ICP (CVPR 2024 · similarity 0.89)
- Rectified Point Flow: Generic Point Cloud Pose Estimation (NeurIPS 2025 · similarity 0.89)
- VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow (CVPR 2025 · similarity 0.88)
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.