AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Chris Metzler, Ali Mousavi, Richard Baraniuk

NeurIPS 2017 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 189 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
unroll D-AMP with learned DnCNN denoisers and retain the Onsager correctionImage compressive recovery · Gaussian measurements, m/n=0.10–0.25PSNR: 23.1 -> 23.7; 25.1 -> 25.7; 26.6 -> 27.2; 27.9 -> 28.5Improved
use unrolled D-AMP with learned DnCNN denoisersImage compressive recovery · Coded diffraction, m/n=0.10–0.25PSNR: 24.0 -> 25.3; 25.7 -> 27.4; 27.5 -> 28.9; 29.1 -> 30.5Improved
add the Onsager correction to D-IT (ablation)Learned D-AMP image recovery · Gaussian measurements, m/n=0.10–0.25PSNR: 20.1 -> 23.7; 20.7 -> 25.7; 21.1 -> 27.2; 21.7 -> 28.5Improved
train LDAMP layers sequentially instead of end-to-end (ablation)LDAMP · Gaussian measurements, trained and tested at m/n=0.20PSNR: 33.1 -> 33.1No clear effect
train denoisers separately on AWGN denoising problems (ablation)LDAMP · Gaussian measurements, trained and tested at m/n=0.20PSNR: 33.1 -> 31.6Hurt
train denoisers separately without tying training to a sampling rate (ablation)LDAMP · Gaussian measurements, trained at m/n=0.20 and tested at m/n=0.05PSNR: 18.7 -> 25.9Improved

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