AI Paper Atlas

Research map / Image generation / Image restoration

Raw Image Reconstruction With Learned Compact Metadata

Yufei Wang, Yi Yu, Wenhan Yang, Lanqing Guo, Lap-Pui Chau, Alex C. Kot, Bihan Wen

CVPR 2023 · Image generation › Image restoration · approach: Learned image compression · 19 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
learn a compact latent-space metadata representation end-to-end instead of sampling raw pixelsRaw image reconstruction · AdobeFiveKPSNR: 56.72 -> 58.14Improved
add learned compact latent-space metadata (ablation)Ours · AdobeFiveKPSNR: 53.03 -> 58.14Improved
add saved channel means m(v) to the hyper-prior metadata (ablation)Ours · NUS, meanPSNR: 58.66 -> 58.79Improved
add saved channel means m(v) to the hyper-prior metadata (ablation)Ours · NUS, meanbpp: 2.92e-4 -> 2.89e-4Improved
replace the sRGB-guided context model with the checkerboard context model (ablation)Ours · NUS, compressed JPEG imagesbppHurt
use already decoded latent features as context for estimating the remaining latent distribution (ablation)sRGB-guided context model · Raw image reconstructionbppImproved
adapt metadata bit allocation to image content in latent spaceOurs · Raw image reconstructionPSNRImproved

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