AI Paper Atlas

Research map / Image generation / Image restoration

Scalable Convolutional Neural Network for Image Compressed Sensing

Wuzhen Shi, Feng Jiang, Shaohui Liu, Debin Zhao

CVPR 2019 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 175 citations (OpenAlex)

Check 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 CSNet's reconstruction network with SCSNet's hierarchical reconstruction networkCSNet · Set5, Set14, BSD100 average across seven sampling ratiosPSNR: 31.90 -> 32.40Improved
Replace CSNet's reconstruction network with SCSNet's hierarchical reconstruction networkCSNet · Set5, Set14, BSD100 average across seven sampling ratiosSSIM: 0.8445 -> 0.8507Improved
Use SCSNet instead of the strongest listed baseline, ISTA-Net+ISTA-Net+ · Set11, sampling ratio 0.5PSNR: 38.07 -> 39.01Improved
Use SCSNet instead of CSNetCSNet · Set11, sampling ratio 0.1PSNR: 28.10 -> 28.48Improved
Use SCSNet instead of CSNetCSNet · BSD68, sampling ratio 0.5PSNR: 34.89 -> 35.77Improved
Use SCSNet instead of CSNetCSNet · BSD68, sampling ratio 0.1PSNR: 27.10 -> 27.28Improved
Order measurement bases with the greedy validation-set selection method instead of random selection (ablation)SCSNet · Set5 and Set14, progressive sampling with the base layerPSNRImproved
Use one trained model and remove selected measurement bases for intermediate sampling ratiosSCSNet · Sampling ratios between trained layer ratiosPSNRImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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