Research map / Point clouds / Point cloud classification
Self-Supervised 3D Scene Flow Estimation Guided by Superpoints
Yaqi Shen, Le Hui, Jin Xie, Jian Yang
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 |
|---|---|---|---|
| replace point-level GRU refinement with superpoint generation and superpoint-guided refinement (ablation) | SPFlowNet · KITTI_o | EPE: 0.119 -> 0.086 | Improved |
| use flow-guided superpoint generation instead of SPNet generation without flow guidance (ablation) | SPFlowNet · KITTI_o | EPE: 0.090 -> 0.086 | Improved |
| add superpoint consistency encoding (ablation) | SPFlowNet · KITTI_o | EPE: 0.103 -> 0.086 | Improved |
| add the consistency loss (ablation) | SPFlowNet · KITTI_o | EPE: 0.094 -> 0.086 | Improved |
| set the number of superpoints to 30 (ablation) | SPFlowNet · KITTI_o | AS | Improved |
| set the number of nearest superpoint centers to 2 (ablation) | SPFlowNet · KITTI_o | AS | Improved |
| use 3 refinement iterations rather than 4 or 5 (ablation) | SPFlowNet · KITTI_o | inference time | 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.
- RigidFlow — RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior (CVPR 2022) · better on 7 of 7 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
- Self-Point-Flow: Self-Supervised Scene Flow Estimation From Point Clouds With Optimal Transport and Random Walk (CVPR 2021 · similarity 0.90)
- SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow (CVPR 2023 · similarity 0.90)
- Learning Scene Dynamics from Point Cloud Sequences (IJCV 2022 · similarity 0.89)
- Self-Supervised 3D Scene Flow Estimation and Motion Prediction Using Local Rigidity Prior (TPAMI 2024 · similarity 0.89)
- RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior (CVPR 2022 · similarity 0.89)
- ZeroFlow: Scalable Scene Flow via Distillation (ICLR 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.
