Research map / Architectures and efficiency / CNN design
Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation
Feihu Zhang, Oliver J. Woodford, Victor Adrian Prisacariu, Philip H.S. Torr
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 the separable cost volume module | RAFT · KITTI-15 train (trained on C+T) | Fl-all (%): 17.4 -> 15.9 | Improved |
| add the separable cost volume module | PWC-Net · KITTI-15 train (trained on C+T) | Fl-all (%): 33.7 -> 23.1 | Improved |
| add the separable cost volume module | RAFT · Sintel train clean (trained on C+T) | EPE: 1.43 -> 1.30 | Improved |
| add extra Virtual KITTI synthetic training data | Separable Flow · KITTI-15 train (trained on C+T) | Fl-all (%): 15.9 -> 7.74 | Improved |
| add attention channels to mean and max separation (ablation) | Separable Flow · KITTI-15 train (trained on C+T) | Fl-all (%): 16.7 -> 15.9 | Improved |
| add attention channels to max-only separation (ablation) | Separable Flow · KITTI-15 train (trained on C+T) | Fl-all (%): 16.5 -> 15.9 | Improved |
| use 4x SGA layers instead of 2x 3D conv aggregation (ablation) | Separable Flow · KITTI-15 train (trained on C+T) | Fl-all (%): 16.8 -> 15.9 | Improved |
| use 4x SGA layers instead of 8x 3D conv (ablation) | Separable Flow · KITTI-15 train (trained on C+T) | Fl-all (%): 16.4 -> 15.9 | Improved |
| use separate aggregation weights for u and v instead of shared (ablation) | Separable Flow · KITTI-15 train (trained on C+T) | Fl-all (%): 16.3 -> 15.9 | Improved |
| use UNet aggregation block instead of ResNet (ablation) | Separable Flow · KITTI-15 train (trained on C+T) | Fl-all (%): 16.1 -> 15.9 | Improved |
| add motion regression initialization (ablation) | Separable Flow · KITTI-15 train (trained on C+T) | Fl-all (%): 16.8 -> 15.9 | Improved |
| add motion regression initialization (ablation) | Separable Flow · Sintel train clean (trained on C+T) | EPE: 1.37 -> 1.30 | Improved |
Later papers that compared with this method
3 later accepted papers report SeparableFlow as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- FlowNAS: Neural Architecture Search for Optical Flow Estimation (IJCV 2023 · better on 0 of 4 shared results)
- SKFlow: Learning Optical Flow with Super Kernels (NeurIPS 2022 · better on 2 of 3 shared results)
- Disentangling Architecture and Training for Optical Flow (ECCV 2022 · better on 1 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- RAFT — RAFT: Recurrent All-Pairs Field Transforms for Optical Flow (ECCV 2020) · better on 8 of 8 shared results
- PWC-Net — PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume (CVPR 2018) · 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
- Learning Optical Flow From Still Images (CVPR 2021 · similarity 0.90)
- Explicit Motion Disentangling for Efficient Optical Flow Estimation (ICCV 2023 · similarity 0.90)
- Learning Optical Flow From a Few Matches (CVPR 2021 · similarity 0.90)
- UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model (CVPR 2024 · similarity 0.89)
- Recurrent Partial Kernel Network for Efficient Optical Flow Estimation (AAAI 2024 · similarity 0.89)
- StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences (NeurIPS 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.
