AI Paper Atlas

Research map / Image generation / Image restoration

Content-Oriented Learned Image Compression

Meng Li, Shangyin Gao, Yihui Feng, Yibo Shi, Jing Wang

ECCV 2022 · Image generation › Image restoration · approach: Learned image compression

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 MAE, LPIPS and GAN perceptual losses to an MSE-only model (ablation)COLIC · Kodak (kodim14, ~0.2 bpp)visual quality (qualitative)Mixed
add Laplacian loss on structure regions to the perceptual loss (ablation)COLIC · Kodak (kodim14, ~0.2 bpp)visual quality (qualitative)Improved
add MSE face loss on small face regions (ablation)COLIC · Kodak (kodim14, ~0.2 bpp)visual quality (qualitative)Improved
use asymmetric Gaussian entropy model instead of general Gaussian (ablation)COLIC · KodakBD-rate: about 0.68% BD-rate reductionImproved
add average pooling after each deconvolution layer (ablation)COLIC · Kodakcheckerboard artifacts (qualitative)Improved
use relativistic average PatchGAN discriminator instead of HiFiC discriminator (ablation)COLIC · Kodakdetail preservation (qualitative)Improved
use COLIC instead of HiFiCCOLIC · KodakPSNR, SSIM, FIDImproved

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