AI Paper Atlas

Research map / Image generation / Image restoration

JPEG Artifacts Removal via Contrastive Representation Learning

Xi Wang, Xueyang Fu, Yurui Zhu, Zheng-Jun Zha

ECCV 2022 · Image generation › Image restoration · approach: Learned image compression · 30 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
add the contrastively pre-trained compression quality encoder (ablation)blind JPEG artifacts removal network · Classic5 Q10PSNR (dB): 29.97 -> 30.16Improved
add pre-training of the compression quality encoder (vs joint training without it) (ablation)blind JPEG artifacts removal network · Classic5 Q10PSNR (dB): 30.04 -> 30.16Improved
add invertible neural module fusion instead of concat and conv (ablation)blind JPEG artifacts removal network · Classic5 Q10PSNR (dB): 30.11 -> 30.16Improved
add INM and EFFM fusion instead of concat and conv (ablation)blind JPEG artifacts removal network · Classic5 Q10PSNR (dB): 30.09 -> 30.16Improved
add FFT loss (ablation)blind JPEG artifacts removal network · Classic5 Q10PSNR (dB): 30.03 -> 30.16Improved
add FFT loss (ablation)blind JPEG artifacts removal network · Classic5 Q40PSNR (dB): 34.32 -> 34.43Improved
add compression quality encoder (ablation)blind JPEG artifacts removal network · Classic5 Q40PSNR (dB): 34.31 -> 34.43Improved
use single contrastive model versus FBCNNblind JPEG artifacts removal network · LIVE1 Q10PSNR (dB): 29.75 -> 29.80Improved
use contrastive model versus FBCNN on unseen qualityblind JPEG artifacts removal network · Classic5 Q15PSNR (dB): 31.42 -> 31.37No clear effect
use contrastive model versus FBCNN on color ICBblind JPEG artifacts removal network · ICB color Q10PSNR (dB): 32.18 -> 32.05Hurt

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