AI Paper Atlas

Research map / Image generation / Image restoration

CADC: Content Adaptive Diffusion-Based Generative Image Compression

Xihua Sheng, Lingyu Zhu, Tianyu Zhang, Dong Liu, Shiqi Wang, Jing Wang

CVPR 2026 · Image generation › Image restoration · approach: Perceptual diffusion image compression · 3 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 Uncertainty-Guided Adaptive Quantization (ablation)CADC diffusion codec (Kodak) · KodakLPIPS BD-rate: BD-rate 0.00% -> -3.7%Improved
add UGAQ (ablation)CADC diffusion codec (Kodak) · KodakDISTS BD-rate: BD-rate 0.00% -> -2.7%Improved
add Auxiliary Decoder-Guided Information Concentration (ablation)CADC diffusion codec (Kodak) · KodakLPIPS BD-rate: BD-rate -3.7% -> -5.3%Improved
add ADGIC (ablation)CADC diffusion codec (Kodak) · KodakDISTS BD-rate: BD-rate -2.7% -> -3.5%Improved
add Bitrate-Free Adaptive Textual Conditioning (ablation)CADC diffusion codec (Kodak) · KodakLPIPS BD-rate: BD-rate -5.3% -> -6.8%Improved
add BFATC (ablation)CADC diffusion codec (Kodak) · KodakDISTS BD-rate: BD-rate -3.5% -> -5.5%Improved
CADC versus other diffusion codecs (DiffEIC, ResULIC, MKIC, OSCAR, StableCodec)CADC · Kodak, DIV2K Val, CLIC 2020 TestLPIPS, DISTS, FID, KIDImproved

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