AI Paper Atlas

Research map / Image generation / Image restoration

Quantization Guided JPEG Artifact Correction

Max Ehrlich, Ser-Nam Lim, Larry Davis, Abhinav Shrivastava

ECCV 2020 · Image generation › Image restoration · approach: Learned image compression · 118 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 a single quantization-guided model instead of IDCN's mismatched quality-10 model on quality-50 imagesQuantization Guided JPEG Artifact Correction · Live-1 generalization (image quality 50)PSNR: 30.19 -> 32.78Improved
use a single quantization-guided model instead of IDCN's mismatched quality-20 model on quality-50 imagesQuantization Guided JPEG Artifact Correction · Live-1 generalization (image quality 50)PSNR: 31.91 -> 32.78Improved
use a single quantization-guided model instead of IDCN's quality-10 model on quality-20 imagesQuantization Guided JPEG Artifact Correction · Live-1 generalization (image quality 20)PSNR: 29.25 -> 29.92Improved
use a single quantization-guided model instead of IDCN's quality-20 model on quality-10 imagesQuantization Guided JPEG Artifact Correction · Live-1 generalization (image quality 10)PSNR: 26.95 -> 27.65Improved
apply IDCN quality-10 model to quality-50 images versus leaving JPEG untouchedIDCN · Live-1 generalization (image quality 50)PSNR: 30.91 -> 30.19Hurt
replace CFM layers with channelwise concatenation of the quantization matrix or ignoring it (ablation)Quantization Guided JPEG Artifact Correction · Classic-5 quality 10 (Y channel)PSNRImproved
add BlockNet before FrequencyNet instead of FrequencyNet alone (ablation)Quantization Guided JPEG Artifact Correction · Classic-5 quality 10 (Y channel)PSNRImproved
add the fusion layer (ablation)Quantization Guided JPEG Artifact Correction · Classic-5 quality 10 (Y channel)PSNRImproved
add GAN loss training (Ours-GAN) to the regression modelQuantization Guided JPEG Artifact Correction · Live-1, BSDS500, ICBFIDImproved

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