Research map / 3D vision / Depth and stereo
CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation
Haisong Liu, Tao Lu, Yihui Xu, Jia Liu, Wenjie Li, Lijun Chen
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 bidirectional fusion instead of the best unidirectional fusion (ablation) | CamLiFlow · FlyingThings3D val | EPE2D: 2.25 to 2.18 | Improved |
| Use bidirectional fusion instead of the best unidirectional fusion (ablation) | CamLiFlow · FlyingThings3D val | EPE3D: 0.036 to 0.033 | Improved |
| Fuse pyramid, cost-volume, and flow-decoder features at all three stages (ablation) | CamLiFlow · FlyingThings3D val | EPE2D: 2.29 to 2.18 | Improved |
| Add learnable nearest-neighbor interpolation to direct point projection (ablation) | CamLiFlow Bi-CLFM · FlyingThings3D val | EPE2D: 2.30 to 2.24 | Improved |
| Add 2D similarity measurements to interpolation (ablation) | CamLiFlow Bi-CLFM · FlyingThings3D val | EPE2D: 2.24 to 2.18 | Improved |
| Increase interpolation neighbors from k=1 to k=3 with MEAN or MAX aggregation (ablation) | CamLiFlow Bi-CLFM · FlyingThings3D val | EPE2D: 2.18; 2.19; 2.19 | No clear effect |
| Apply inverse depth scaling to point coordinates (ablation) | CamLiFlow · FlyingThings3D val | EPE3D: 0.036 to 0.033 | Improved |
| Apply inverse depth scaling to point coordinates (ablation) | CamLiFlow LiDAR-only · FlyingThings3D val | EPE3D: 0.073 to 0.068 | Improved |
| Add background rigidity refinement (ablation) | CamLiFlow · KITTI Scene Flow test | SF-all: 5.62 to 4.43 | Improved |
| Omit robust-loss fine-tuning (ablation) | CamLiFlow · FlyingThings3D val | ACC1px: 84.3% to 87.3% | Hurt |
| Detach gradients between modality branches in Bi-CLFM (ablation) | CamLiFlow · FlyingThings3D val | 3D branch performance | Improved |
| Add batch normalization to the feature pyramid (ablation) | CamLiFlow · Training | training stability | Improved |
Later papers that compared with this method
4 later accepted papers report CamLiFlow as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- x^2-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Space (CVPR 2026 · better on 4 of 4 shared results)
- SEA-Flow3D: Simplified, Efficient, and Accurate Scene Flow via Spatial Vector Sampling and Multi-scale Refinement (CVPR 2026 · better on 1 of 1 shared result)
- RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation (ICCV 2023 · better on 6 of 6 shared results)
- Learning Optical Expansion From Scale Matching (CVPR 2023 · better on 0 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.
- RAFT-3D — RAFT-3D: Scene Flow Using Rigid-Motion Embeddings (CVPR 2021) · better on 2 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
- Learning Optical Flow and Scene Flow With Bidirectional Camera-LiDAR Fusion (TPAMI 2023 · similarity 0.96)
- SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data (ECCV 2026 · similarity 0.89)
- RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation (ICCV 2023 · similarity 0.88)
- Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow (CVPR 2024 · similarity 0.86)
- ICP-Flow: LiDAR Scene Flow Estimation with ICP (CVPR 2024 · similarity 0.86)
- DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method (NeurIPS 2025 · similarity 0.85)
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.
