Research map / Point clouds / Point cloud classification
DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds
Chensheng Peng, Guangming Wang, Xian Wan Lo, Xinrui Wu, Chenfeng Xu, Masayoshi Tomizuka, Wei Zhan, Hesheng Wang
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 dense 2D representation of all points instead of 8192 sampled points (ablation) | DELFlow · FlyingThings3D val | EPE_3D: 0.061 -> 0.058 | Improved |
| add warping operation (ablation) | DELFlow · FlyingThings3D val | EPE_3D: 0.433 -> 0.058 | Improved |
| add warping projection in cost volume (vs direct projection) (ablation) | DELFlow · FlyingThings3D val | EPE_3D: 0.105 -> 0.058 | Improved |
| add image-point feature fusion (attentive) (ablation) | DELFlow · FlyingThings3D val | EPE_2D: 4.32 -> 2.02 | Improved |
| attentive fusion instead of concatenation (ablation) | DELFlow · FlyingThings3D val | EPE_2D: 3.26 -> 2.02 | Improved |
| add kernel-based grouping instead of KNN over all points (ablation) | DELFlow · FlyingThings3D val | accuracy: EPE_3D 0.056 -> 0.058 | No clear effect |
| add kernel-based grouping instead of KNN over all points (ablation) | DELFlow · Inference time (56269 points) | time (ms): 1324.29 -> 52.91 | 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.
- PointPWC-Net — PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation (ECCV 2020) · better on 1 of 1 shared result
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
- Deep Scene Flow Learning: From 2D Images to 3D Point Clouds (TPAMI 2023 · similarity 0.90)
- PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation (ECCV 2020 · similarity 0.90)
- PointFlowNet: Learning Representations for Rigid Motion Estimation From Point Clouds (CVPR 2019 · similarity 0.89)
- SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation (AAAI 2022 · similarity 0.89)
- Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations (CVPR 2025 · similarity 0.88)
- ZeroFlow: Scalable Scene Flow via Distillation (ICLR 2024 · 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.
