Image Restoration using Plug-and-Play CNN MAP Denoisers

December 18, 2019 · Entered Twilight · 🏛 VISIGRAPP

"Last commit was 6.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitattributes, .gitignore, LICENSE, MAPDeblurer_color.ipynb, MAPDeblurer_gray.ipynb, MAPInpainter_gray.ipynb, MAPdenoiser.py, MAPinpainting.py, README.md, data, fastMAPdeblurer.py, img, models, utils.py

Authors Siavash Bigdeli, David Honzátko, Sabine Süsstrunk, L. Andrea Dunbar arXiv ID 1912.09299 Category eess.IV: Image & Video Processing Cross-listed cs.CV, cs.LG Citations 8 Venue VISIGRAPP Repository https://github.com/DawyD/cnn-map-denoiser ⭐ 13 Last Checked 1 month ago

Abstract

Plug-and-play denoisers can be used to perform generic image restoration tasks independent of the degradation type. These methods build on the fact that the Maximum a Posteriori (MAP) optimization can be solved using smaller sub-problems, including a MAP denoising optimization. We present the first end-to-end approach to MAP estimation for image denoising using deep neural networks. We show that our method is guaranteed to minimize the MAP denoising objective, which is then used in an optimization algorithm for generic image restoration. We provide theoretical analysis of our approach and show the quantitative performance of our method in several experiments. Our experimental results show that the proposed method can achieve 70x faster performance compared to the state-of-the-art, while maintaining the theoretical perspective of MAP.