AI Paper Atlas

Research map / Image generation / Image restoration

Distort-and-Recover: Color Enhancement Using Deep Reinforcement Learning

Jongchan Park, Joon-Young Lee, Donggeun Yoo, In So Kweon

CVPR 2018 · Image generation › Image restoration · approach: Low-light image enhancement · 228 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
Use distort-and-recover DRL instead of Pix2Pix on distorted-reference training pairsColor enhancement on MIT-Adobe FiveK Random 250 · Random 250mean L² error: 14.46 -> 12.15Improved
Use distort-and-recover DRL instead of Pix2Pix on distorted-reference training pairsColor enhancement on MIT-Adobe FiveK Random 250 · Random 250SSIM: 0.699 -> 0.910Improved
Add contextual VGG features to the Lab histogram (ablation)Color enhancement agent · Random 250mean L² error: 12.30 -> 10.99Improved
Use a CIELab histogram with context instead of six color features (ablation)Color enhancement agent · Random 250mean L² error: 12.53 -> 10.99Improved
Replace the CIELab histogram with RGB-L histogram (ablation)Color enhancement agent · Random 250mean L² error: 10.99 -> 12.62Hurt
Replace the CIELab histogram with TinyImage (ablation)Color enhancement agent · Random 250mean L² error: 10.99 -> 15.07Hurt
Augment Pix2Pix training pairs 10 times instead of using no augmentation (ablation)Pix2Pix with distort-and-recover training · Random 250mean L² error: 14.46 -> 13.79Improved
Increase Pix2Pix augmentation from 10 times to 20 times (ablation)Pix2Pix with distort-and-recover training · Random 250mean L² error: 13.79 -> 13.59Improved
Increase Pix2Pix augmentation from 20 times to 30 times (ablation)Pix2Pix with distort-and-recover training · Random 250mean L² error: 13.59 -> 13.60No clear effect
Train with Nashville-filtered reference images using distort-and-recoverColor enhancement agent · MIT-Adobe FiveK Random 250 (Nashville style)mean L² error: 27.78 -> 17.87Improved
Use the proposed method instead of Pix2Pix trained with Shutterstock referencesColor enhancement user study · MIT-Adobe FiveK user studyMean score: 2.09 -> 2.86Improved
Use the proposed method instead of Lightroom auto adjustmentsColor enhancement user study · MIT-Adobe FiveK user studyMean score: 2.74 -> 2.86Improved

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