papers AI Learner
The Github is limit! Click to go to the new site.

Self-Supervised Deep Image Denoising

2019-01-29
Samuli Laine, Jaakko Lehtinen, Timo Aila

Abstract

We describe techniques for training high-quality image denoising models that require only single instances of corrupted images as training data. Inspired by a recent technique that removes the need for supervision through image pairs by employing networks with a “blind spot” in the receptive field, we address two of its shortcomings: inefficient training and somewhat disappointing final denoising performance. This is achieved through a novel blind-spot convolutional network architecture that allows efficient self-supervised training, as well as application of Bayesian distribution prediction on output colors. Together, they bring the self-supervised model on par with fully supervised deep learning techniques in terms of both quality and training speed in the case of i.i.d. Gaussian noise.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.10277

PDF

http://arxiv.org/pdf/1901.10277


Similar Posts

Comments