AI Paper Atlas

Research map / Image generation / Image restoration

Neural Proximal Gradient Descent for Compressive Imaging

Morteza Mardani, Qingyun Sun, David Donoho, Vardan Papyan, Hatef Monajemi, Shreyas Vasanawala, John Pauly

NeurIPS 2018 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 115 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 recurrent proximal-gradient iterations with a shared small ResNet instead of a single deep ResNetMRI reconstruction · Pediatric abdominal MRI testSNR (dB): 24.33 -> 26.07Improved
Use recurrent proximal-gradient iterations with a shared small ResNet instead of CS-WVMRI reconstruction · Pediatric abdominal MRI testSNR (dB): 22.51 -> 26.07Improved
Use recurrent proximal-gradient iterations with a shared small ResNet instead of CS-WVMRI reconstruction · Pediatric abdominal MRI testInference time (sec): 1.16 -> 0.04Improved
Use 5 iterations and 2 RBs instead of 10 iterations and 1 RB (ablation)Neural proximal gradient descent · Pediatric abdominal MRI testSNR (dB): 26.07 -> 26.94Improved
Use 5 iterations and 2 RBs instead of 10 iterations and 1 RB (ablation)Neural proximal gradient descent · Pediatric abdominal MRI testSSIM: 0.9117 -> 0.9221Improved
Use 5 iterations and 2 RBs instead of 10 iterations and 1 RB (ablation)Neural proximal gradient descent · Pediatric abdominal MRI testInference time (sec): 0.04 -> 0.10Hurt
Use 2 iterations and 5 RBs instead of 10 iterations and 1 RB (ablation)Neural proximal gradient descent · Pediatric abdominal MRI testSNR (dB): 26.07 -> 26.55Improved
Use 2 iterations and 5 RBs instead of 10 iterations and 1 RB (ablation)Neural proximal gradient descent · Pediatric abdominal MRI testInference time (sec): 0.04 -> 0.12Hurt
Add more than 5 RBs to a single-iteration network (ablation)MRI reconstruction · Pediatric abdominal MRISNR (dB): 24.15; 24.33No clear effect
Increase recurrent copies from one to three (ablation)Neural proximal gradient descent with 1 RB · Pediatric abdominal MRISNR (dB): more than 2dBImproved
Increase recurrent copies from one to three (ablation)Neural proximal gradient descent with 2 RBs · Pediatric abdominal MRISNR (dB): more than 3dBImproved

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