Reproduce “Improved Total Variation based Image Compressive Sensing Recovery by Nonlocal Regularization” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jian Zhang, Shaohui Liu, Debin Zhao, Ruiqin Xiong, Siwei Ma
TVNLR combines total-variation regularization with an NLM-based nonlocal term to recover images from compressed-sensing measurements. It uses local edge information and similarities between patches elsewhere in an image. On four conventional images and four synthetic measurement ratios, it outperformed TVAL3 in all 16 PSNR comparisons; for Barbara at 30% measurements, it scored 28.39 dB versus 26.32 dB. It took roughly 2.4 times as long.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.