AI Paper Atlas

Research map / Image generation / Image restoration

Conditional Probability Models for Deep Image Compression

Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc Van Gool

CVPR 2018 · Image generation › Image restoration · approach: Learned image compression · 528 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
Replace the uniform prior with the proposed 3D-CNN context model (ablation)Fixed auto-encoder (L=6, K=16) · Kodakrate: 0.646 bpp -> 0.579 bppImproved
Replace the uniform prior with a zeroth-order symbol histogram (ablation)Fixed auto-encoder (L=6, K=16) · Kodakrate: 0.646 bpp -> 0.642 bppImproved
Replace the uniform prior with a one-step conditional histogram (ablation)Fixed auto-encoder (L=6, K=16) · Kodakrate: 0.646 bpp -> 0.627 bppImproved
Use the proposed 3D-CNN context model instead of a first-order histogram (ablation)Fixed auto-encoder (L=6, K=16) · Kodakrate: 0.627 bpp -> 0.579 bppImproved
Train the context model jointly with the auto-encoder rather than separately after training (ablation)Masked 3D-CNN context model and auto-encoder · Kodakrate: 22% reduction in bppImproved
Clip the rate term using a target bitrate (ablation)Proposed compression model · Image compressionperformanceNo clear effect

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