Research map / Probabilistic and scientific modeling / Molecules and proteins
Robust Interpolation of Correspondences for Large Displacement Optical Flow
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 |
|---|---|---|---|
| Replace Epic interpolation with Ric interpolation using CPM matches | Optical flow interpolation · MPI-Sintel train, with variational refinement | EPE: 3.54 -> 3.52 | Helped |
| Replace Epic interpolation with Ric interpolation using CPM matches | Optical flow interpolation · KITTI-2012 train, with variational refinement | EPE: 3.17 -> 2.81 | Helped |
| Replace Epic interpolation with Ric interpolation using CPM matches | Optical flow interpolation · KITTI-2015 train, with variational refinement | EPE: 7.71 -> 7.12 | Helped |
| Replace Epic interpolation with Ric interpolation using CPM matches | Optical flow interpolation · MPI-Sintel train, with variational refinement | Error percentage (EPE ≥3 pixels): 10.08 -> 8.95 | Helped |
| Replace Epic interpolation with Ric interpolation using CPM matches | Optical flow interpolation · KITTI-2012 train, with variational refinement | Error percentage (EPE ≥3 pixels): 13.32 -> 10.15 | Helped |
| Replace Epic interpolation with Ric interpolation using CPM matches | Optical flow interpolation · KITTI-2015 train, with variational refinement | Error percentage (EPE ≥3 pixels): 23.52 -> 20.34 | Helped |
| Use Ric instead of Epic interpolation with KPM matches | Optical flow interpolation · MPI-Sintel train, with variational refinement | EPE: 6.74 -> 6.93 | Hurt |
| Use Ric instead of Epic interpolation with KPM matches | Optical flow interpolation · KITTI-2015 train, with variational refinement | EPE: 26.01 -> 25.35 | Hurt |
| Use Ric instead of Epic interpolation with KPM matches | Optical flow interpolation · MPI-Sintel train, with variational refinement | Error percentage (EPE ≥3 pixels): 16.64 -> 15.86 | Helped |
| Use CPM matches rather than low-density KPM matches | RicFlow · MPI-Sintel train | EPE | Helped |
| Add model propagation instead of estimating each piecewise model independently (ablation) | RicFlow · MPI-Sintel | EPE | Helped |
| Add model propagation instead of estimating each piecewise model independently (ablation) | RicFlow · MPI-Sintel | running time | Helped |
Closest papers by meaning
- UFM: A Simple Path towards Unified Dense Correspondence with Flow (NeurIPS 2025 · similarity 0.86)
- Sparse Global Matching for Video Frame Interpolation with Large Motion (CVPR 2024 · similarity 0.86)
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation (CVPR 2024 · similarity 0.85)
- SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model (AAAI 2024 · similarity 0.85)
- Hierarchical Flow Diffusion for Efficient Frame Interpolation (CVPR 2025 · similarity 0.85)
- Asymmetric Flow Models (NeurIPS 2026 · 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.