AI Paper Atlas

Research map / Image generation / Image restoration

ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing

CVPR 2018 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 1,329 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 image-domain sparsification with explicit residual-domain sparsification and skip connectionsISTA-Net · Set11, 25% CS ratioPSNR: ISTA-Net achieves about 1 dB gain over ISTA-NetHelped
add ReLU nonlinear transforms rather than using linear transforms (ablation)ISTA-Net+ · Set11PSNRHelped
add ReLU nonlinear transforms to improve training stability (ablation)ISTA-Net+ · Set11training stabilityHelped
share step sizes, thresholds, and transforms across phases instead of keeping them unshared (ablation)ISTA-Net+ · Set11, 25% CS ratioPSNR: 32.57 -> 31.53Hurt
share step sizes and transforms across phases, leaving thresholds unshared (ablation)ISTA-Net+ · Set11, 25% CS ratioPSNR: 32.57 -> 32.28Hurt
share thresholds and transforms across phases, leaving step sizes unshared (ablation)ISTA-Net+ · Set11, 25% CS ratioPSNR: 32.57 -> 32.08Hurt
share transforms across phases, leaving step sizes and thresholds unshared (ablation)ISTA-Net+ · Set11, 25% CS ratioPSNR: 32.57 -> 32.36Hurt

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