Research map / Point clouds / Point cloud classification
Multi-Scale Bidirectional Recurrent Network with Hybrid Correlation for Point Cloud Based Scene Flow Estimation
Wencan Cheng, Jong Hwan Ko
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 |
|---|---|---|---|
| add iterative bidirectional feature augmentation (IBFA) (ablation) | baseline scene flow network · FT3Ds | EPE3D (m): 0.029 -> 0.025 | Improved |
| add hybrid correlation without IBFA (ablation) | baseline scene flow network · KITTIs | EPE3D (m): 0.030 -> 0.038 | Hurt |
| add hybrid correlation on top of IBFA and GRU (ablation) | MSBRN · FT3Ds | EPE3D (m): 0.019 -> 0.016 | Improved |
| add GRU on top of IBFA and hybrid correlation (ablation) | MSBRN · FT3Ds | EPE3D (m): 0.021 -> 0.016 | Improved |
| use hybrid neighbors (16:16) instead of Euclidean-only (32:0) (ablation) | MSBRN correlation · FT3Ds | EPE3D (m): 0.019 -> 0.016 | Improved |
| use feature-induced neighbors only (0:32) instead of hybrid (ablation) | MSBRN correlation · KITTIs | EPE3D (m): 0.015 -> 0.036 | Hurt |
| increase training iterations Ktr from 1 to 4 (Kin=Ktr) (ablation) | MSBRN BGRU · FT3Ds | EPE3D (m): 0.026 -> 0.015 | Improved |
| increase training iterations from 4 to 5 (ablation) | MSBRN BGRU · FT3Ds | EPE3D (m): 0.015 -> 0.014 | No clear effect |
| use MSBRN instead of iterative single-scale methods | scene flow estimation · runtime | runtime (ms): 972.7ms (FlowStep3D) -> 365.8ms | 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.
- PV-RAFT — PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds (CVPR 2021) · 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
- Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation (ECCV 2022 · similarity 0.91)
- Deep Scene Flow Learning: From 2D Images to 3D Point Clouds (TPAMI 2023 · similarity 0.90)
- FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation (AAAI 2025 · similarity 0.89)
- Recurrent Partial Kernel Network for Efficient Optical Flow Estimation (AAAI 2024 · similarity 0.88)
- DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method (NeurIPS 2025 · similarity 0.87)
- MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting (NeurIPS 2026 · 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.
