Efficient Blind-Spot Neural Network Architecture for Image Denoising

TL;DR

This paper introduces a new convolutional neural network architecture using dilations to efficiently implement blind-spot image denoising, achieving state-of-the-art results without clean training data.

Contribution

A novel fully convolutional network design employing dilations for blind-spot image denoising, surpassing prior methods in performance.

Findings

Improved denoising performance over previous blind-spot methods

Achieved state-of-the-art results on benchmark datasets

Efficient architecture using dilations for blind-spot property

Abstract

Image denoising is an essential tool in computational photography. Standard denoising techniques, which use deep neural networks at their core, require pairs of clean and noisy images for its training. If we do not possess the clean samples, we can use blind-spot neural network architectures, which estimate the pixel value based on the neighbouring pixels only. These networks thus allow training on noisy images directly, as they by-design avoid trivial solutions. Nowadays, the blind-spot is mostly achieved using shifted convolutions or serialization. We propose a novel fully convolutional network architecture that uses dilations to achieve the blind-spot property. Our network improves the performance over the prior work and achieves state-of-the-art results on established datasets.