Research map / Probabilistic and scientific modeling / Molecules and proteins
Full Flow: Optical Flow Estimation By Global Optimization Over Regular Grids
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 patch-based NCC instead of the pixelwise Horn-Schunck data term (ablation) | FullFlow global optimization · MPI Sintel training, final pass, 5% subset | EPE: 5.972 -> 2.710 | Helped |
| Use patch-based NCC instead of the pixelwise Horn-Schunck data term (ablation) | FullFlow global optimization · MPI Sintel training, final pass, 5% subset | EPE: 6.337 -> 2.896 | Helped |
| Use L1 rather than Charbonnier or squared L2 regularization with NCC (ablation) | FullFlow global optimization · MPI Sintel training, final pass, 5% subset | EPE: 2.883 -> 2.710; 2.896 -> 2.710 | Helped |
| Remove truncation from NCC + L1 regularization (ablation) | FullFlow global optimization · MPI Sintel training, final pass, 5% subset | EPE: 2.710 -> 2.710 | No clear effect |
| Remove truncation from NCC + L2 regularization (ablation) | FullFlow global optimization · MPI Sintel training, final pass, 5% subset | EPE: 2.896 -> 2.976 | Hurt |
| Use FullFlow instead of FlowFields | MPI Sintel test · final pass, all | EPE: 5.810 -> 5.895 | Hurt |
| Use FullFlow instead of DiscreteFlow | MPI Sintel test · clean pass, all | EPE: 3.567 -> 3.601 | Hurt |
| Use FullFlow instead of DiscreteFlow | KITTI 2015 test · all | outlier percentage: 22.38% -> 24.26% | Hurt |
Closest papers by meaning
- GMFlow: Learning Optical Flow via Global Matching (CVPR 2022 · similarity 0.88)
- Accurate Optical Flow via Direct Cost Volume Processing (CVPR 2017 · similarity 0.88)
- FlowFM: Advancing Dark Optical Flow Estimation with Flow Matching (CVPR 2026 · similarity 0.88)
- Efficient Coarse-To-Fine PatchMatch for Large Displacement Optical Flow (CVPR 2016 · similarity 0.87)
- DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework (CVPR 2025 · similarity 0.87)
- FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models (CVPR 2024 · 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.