AI Paper Atlas

Research map / Image generation / Image restoration

AdaCS: Adaptive Compressive Sensing With Restricted Isometry Property-Based Error-Clamping

Chenxi Qiu, Xuemei Hu

TPAMI 2024 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 17 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 cascaded feature fusion between stages (ablation)ACCSNet · Set5, rate 0.2PSNR: 36.70 -> 37.19Improved
add cascaded feature fusion between stages (ablation)ACCSNet · BSDS500, rate 0.2PSNR: 32.28 -> 32.67Improved
add cascaded feature fusion between stages (ablation)ACCSNet · Set5, rate 0.05 (stage 1)PSNR: 30.01 -> 30.01No clear effect
add adaptive sampling module (ASM) (ablation)ACCSNet · Set14 and BSD68, stages 2+PSNR: about 1dB improvement in PSNRImproved
patch size 8 instead of 32 (ablation)ACCSNet · General100, rate 0.2PSNR: 35.93 -> 37.23Improved
patch size 8 instead of 16 (ablation)ACCSNet · Set14, rate 0.2PSNR: 32.76 -> 33.27Improved
patch size 8 instead of 16 (ablation)ACCSNet · Set14, rate 0.1PSNR: 29.99 -> 30.00No clear effect
increase sampling scale factor alpha from 0.5 to 0.7 (ablation)ACCSNet · BSDS500 averageSSIM: 0.8275 -> 0.8323Improved
increase sampling scale factor alpha from 0.7 to 0.8 (ablation)ACCSNet · BSDS500 averagePSNR: 30.02 -> 29.72Hurt

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