Research map / Point clouds / Point cloud classification
Neural Scene Flow Prior
Xueqian Li, Jhony Kaesemodel Pontes, Simon Lucey
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 the MLP neural scene-flow prior instead of the graph prior | Scene-flow estimation · KITTI Scene Flow test | Acc5 (%): 63.60±0.09 -> 81.68 ± 2.00 | Improved |
| Use the MLP neural scene-flow prior instead of the graph prior | Scene-flow estimation · Argoverse Scene Flow test | Acc5 (%): 25.24±0.04 -> 38.43 ± 0.48 | Improved |
| Use the MLP neural scene-flow prior instead of the graph prior | Scene-flow estimation · nuScenes Scene Flow test | EPE (m): 0.289 -> 0.175 ± 0.01 | Improved |
| Use the MLP neural scene-flow prior instead of the graph prior | Scene-flow estimation · FlyingThings3D test | Acc5 (%): 29.09 -> 19.16±0.23 | Hurt |
| Add backward flow consistency (ablation) | Neural Scene Flow Prior · KITTI Scene Flow (2,048 points) | EPE (m): 0.113 -> 0.052 | Improved |
| Add backward flow consistency (ablation) | Neural Scene Flow Prior · KITTI Scene Flow (2,048 points) | Acc5 (%): 60.36 -> 80.70 | Improved |
| Add positional encoding to the point coordinates (ablation) | Neural Scene Flow Prior · Scene flow estimation | accuracy | No clear effect |
| Use deeper networks and larger hidden layers (ablation) | Neural Scene Flow Prior · KITTI Scene Flow test | Acc5 (%) | Improved |
| Use Sigmoid instead of ReLU in deeper networks (ablation) | Neural Scene Flow Prior · KITTI Scene Flow test | accuracy | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- PointPWC-Net — PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation (ECCV 2020) · better on 0 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
- Fast Neural Scene Flow (ICCV 2023 · similarity 0.92)
- Deep Scene Flow Learning: From 2D Images to 3D Point Clouds (TPAMI 2023 · similarity 0.91)
- ICP-Flow: LiDAR Scene Flow Estimation with ICP (CVPR 2024 · similarity 0.88)
- Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations (CVPR 2025 · similarity 0.88)
- VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow (CVPR 2025 · similarity 0.88)
- E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization (NeurIPS 2025 · similarity 0.87)
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.
