Reproduce “A Sharpness Based Loss Function for Removing Out-of-Focus Blur” 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
Uditangshu Aurangabadkar, Darren Ramsook, Anil Kokaram
The authors fine-tune an image-restoration network by adding a sharpness score to its pixel-matching objective. They test the same model before and after fine-tuning on 188 real-image crops with low defocus blur. Q rises from 0.079 to 0.084 and LPIPS falls from 0.450 to 0.447, while PSNR slips and SSIM is unchanged; the test establishes no result for stronger blur.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.