Research map / Learning theory and algorithms / Prediction and decision losses
On the Convergence of PatchMatch and Its Variants
Thibaud Ehret, Pablo Arias
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 |
|---|---|---|---|
| Use centered random search instead of uniform random search (ablation) | PatchMatch · Random noise images | convergence rate | Improved |
| Replace centered random search with uniform search over the database image (ablation) | PatchMatch · Random noise images | convergence rate | Hurt |
| Use the worst-case transition probability rather than the empirical transition behavior | PatchMatch convergence bound · PatchMatch convergence, ε = 1 | iterations to reach probability 0.2: 178 iterations; 60 were needed | Mixed |
Closest papers by meaning
- PatchMatch Filter: Edge-Aware Filtering Meets Randomized Search for Visual Correspondence (TPAMI 2016 · similarity 0.86)
- Coherency Sensitive Hashing (TPAMI 2016 · similarity 0.85)
- PatchmatchNet: Learned Multi-View Patchmatch Stereo (CVPR 2021 · similarity 0.85)
- Better and Faster: Exponential Loss for Image Patch Matching (ICCV 2019 · similarity 0.85)
- Convolutional Patch Representations for Image Retrieval: An Unsupervised Approach (IJCV 2016 · similarity 0.85)
- Near, far: Patch-ordering enhances vision foundation models' scene understanding (ICLR 2025 · similarity 0.83)
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.
