AI Paper Atlas

Research map / Image generation / Image restoration

Matching Pixels Using Co-Occurrence Statistics

Rotal Kat, Roy Jevnisek, Shai Avidan

CVPR 2018 · Image generation › Image restoration · approach: Image harmonization and color transformation · 51 citations (OpenAlex)

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 changedWhereMeasuredEffect
Replace SSD with co-occurrence statistics while keeping color featuresTemplate matching · Dekel et al. 105 pairs (color features)AUC: 0.43 -> 0.62Improved
Replace SSD with co-occurrence statistics while keeping deep featuresTemplate matching · Dekel et al. 105 pairs (deep features)AUC: 0.55 -> 0.67Improved
Use deep rather than color features with SSDTemplate matching · Dekel et al. 105 pairsAUC: 0.43 -> 0.55Improved
Combine color and deep featuresCoTM · Oron et al. 270 pairs, meanAUC: 0.62 -> 0.63Improved
Use external-set prototypes instead of per-image prototypes (ablation)CoTM with deep features · Oron et al. 270 pairs, meanAUC: 0.62 -> 0.56No clear effect
Use external-set prototypes instead of per-image prototypes (ablation)CoTM with color features · Oron et al. 270 pairs, meanAUC: 0.53 -> 0.53No clear effect
Embed pixel values before template matching instead of applying CoTM directly (ablation)Template matching · Dekel et al. 105 pairsAUC: 0.62 -> 0.57Hurt
Use a 3-dimensional rather than 256-dimensional embedding (ablation)CoETM · Dekel et al. 105 pairsAUC: 0.57 -> 0.52Hurt
Run Lucas-Kanade on co-occurrence-embedded imagesLucas-Kanade registration · Dekel et al. 105 pairsAUC: 0.47 -> 0.52Improved
Run KCF on co-occurrence-embedded imagesKCF tracker · OTBAUC: 0.42 -> 0.47Improved
Use co-occurrence statistics on grayscale pixel values (ablation)CoTM · Template matchingAUCHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy