AI Paper Atlas

Research map / Image generation / Image restoration

Coarse-to-Fine Hyper-Prior Modeling for Learned Image Compression

Yueyu Hu, Wenhan Yang, Jiaying Liu

AAAI 2020 · Image generation › Image restoration · approach: Learned image compression · 133 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 signal-preserving hyper transform with extra hyper-prior layer (ablation)Hyper-prior (Balle et al. 2018) · KodakR-D (PSNR vs bpp)Improved
add extra hyper layer using original transforms (ablation)Hyper-prior (Balle et al. 2018) · KodakR-D (PSNR vs bpp)No clear effect
add Information Aggregation Reconstruction sub-network (ablation)multi-layer hyper-prior model · KodakR-D (PSNR vs bpp)Improved
replace context model with coarse-to-fine hyper-priorlearned image codec · large 1512x2040 imagesGPU acceleration ratio (encoder): 163.3% vs 128.1%Improved
coarse-to-fine hyper-prior vs context model + hyper-priorlearned image codec · TecnickR-D (PSNR vs bpp)Improved

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