AI Paper Atlas

Research map / Image generation / Image restoration

Early Exit Or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images

Qunliang Xing, Mai Xu, Tianyi Li, Zhenyu Guan

ECCV 2020 · Image generation › Image restoration · approach: Learned image compression · 58 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
use RBQE instead of second-best CBDNetblind enhancement · HEVC-MSP test averageDelta PSNR (dB): 0.409 -> 0.510Improved
use RBQE instead of DnCNNblind enhancement · HEVC-MSP test averageDelta PSNR (dB): 0.317 -> 0.510Improved
use RBQE instead of QE-CNNblind enhancement · HEVC-MSP test averageDelta PSNR (dB): 0.223 -> 0.510Improved
use RBQE instead of CBDNetblind enhancement · JPEG test averageDelta PSNR (dB): 1.500 -> 1.678Improved
early-exit structure: exit at first decoding path instead of last for easiest samples (QP 22) (ablation)RBQE · HEVC-MSP QP 22Delta PSNR (dB): 0.601No clear effect
exit at last decoding path instead of first for hardest samples (QP 42) (ablation)RBQE · HEVC-MSP QP 42Delta PSNR (dB): +0.192 dBImproved
force last exit rather than first exit for QP 22 samples (ablation)RBQE · HEVC-MSP QP 22FLOPs (GMacs): 270% FLOPsHurt
increase quality threshold T_Q (ablation)RBQE · HEVC-MSPDelta PSNR (dB): saturates above 0.89Improved

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