Research map / Point clouds / Point cloud classification
FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
Haiyan Wang, Jiahao Pang, Muhammad A. Lodhi, Yingli Tian, Dong Tian
Check 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 SA² synthesized-point abstraction instead of FPS grouping (ablation) | FESTA · FlyingThings3D test, geo.-only | EPE (m): 0.1402 -> 0.1253 | Improved |
| Use SA² synthesized-point abstraction instead of FPS grouping (ablation) | FESTA · KITTI test, geo.-only | EPE (m): 0.1163 -> 0.0936 | Improved |
| Use TA² feedback and a second iteration instead of Flow Embedding alone (ablation) | FESTA · FlyingThings3D test, geo.-only | EPE (m): 0.1381 -> 0.1253 | Improved |
| Use TA² feedback and a second iteration instead of Flow Embedding alone (ablation) | FESTA · KITTI test, geo.-only | EPE (m): 0.1027 -> 0.0936 | Improved |
| Add existence-mask prediction as an auxiliary task (ablation) | FESTA · FlyingThings3D test, geo.-only | EPE (m): 0.1289 -> 0.1253 | Improved |
| Add existence-mask prediction as an auxiliary task (ablation) | FESTA · KITTI test, geo.-only | EPE (m): 0.0955 -> 0.0936 | Improved |
| Replace FPS-based abstraction with SA² | PointNet++ segmentation network · Object segmentation, r=1.8 | accuracy (%): 43.07 -> 69.18 | Improved |
Later papers that compared with this method
2 later accepted papers report FESTA as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- What Matters for 3D Scene Flow Network (ECCV 2022 · better on 2 of 2 shared results)
- FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-World Point Clouds (ECCV 2022 · better on 1 of 1 shared result)
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 9 of 9 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
- Deep Scene Flow Learning: From 2D Images to 3D Point Clouds (TPAMI 2023 · similarity 0.89)
- Learning Scene Dynamics from Point Cloud Sequences (IJCV 2022 · similarity 0.88)
- DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method (NeurIPS 2025 · similarity 0.87)
- FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation (AAAI 2025 · similarity 0.87)
- ZeroFlow: Scalable Scene Flow via Distillation (ICLR 2024 · similarity 0.87)
- Zero-Shot Monocular Scene Flow Estimation in the Wild (CVPR 2025 · 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.
