AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Block Coordinate Plug-and-Play Methods for Blind Inverse Problems

Weijie Gan, Shirin Shoushtari, Yuyang Hu, Jiaming Liu, Hongyu An, Ulugbek Kamilov

NeurIPS 2023 · Learning theory and algorithms › Matrix and tensor methods · approach: Signal recovery and phase retrieval

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 learned deep prior on measurement operator (BC-PnP vs PnP) (ablation)PnP · CS-PMRI R=8RMSE_x: 0.171 -> 0.122Improved
add learned deep prior on measurement operator (BC-PnP vs PnP) (ablation)PnP · CS-PMRI R=6RMSE_x: 0.111 -> 0.091Improved
add learned prior on CSM vs gradient-descent estimation (BC-PnP vs PnP-GD) (ablation)PnP-GD · CS-PMRI R=8RMSE_theta: 0.355 -> 0.337Improved
add learned prior (BC-PnP vs PnP) (ablation)PnP · CS-PMRI R=6SSIM_x: 0.950 -> 0.961Improved
use BC-PnP versus oracle known operatorBC-PnP · CS-PMRI R=6RMSE_x: 0.091 vs 0.069Mixed
BC-PnP versus unsupervised-calibration ISTANet+ISTANet+ · CS-PMRI R=8RMSE_x: 0.140 -> 0.122Improved
add kernel denoiser prior (BC-PnP vs PnP) (ablation)PnP · blind deblurring setting 1RMSE_x: 0.082 -> 0.055Improved
add kernel denoiser prior (BC-PnP vs PnP) (ablation)PnP · blind deblurring setting 2RMSE_x: 0.106 -> 0.098Improved
add kernel prior (BC-PnP vs PnP-GD) (ablation)PnP-GD · blind deblurring setting 1RMSE_theta: 0.283 -> 0.097Improved
add kernel prior (BC-PnP vs PnP-GD) (ablation)PnP-GD · blind deblurring setting 1RMSE_x: 0.082 -> 0.082No clear effect
use BC-PnP versus Pan-DCPPan-DCP · blind deblurring setting 1SSIM_x: 0.835 -> 0.921Improved
use BC-PnP versus oracle kernelBC-PnP · blind deblurring setting 2RMSE_x: 0.098 vs 0.088Mixed

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