Efficient Deep Image Denoising via Class Specific Convolution

TL;DR

This paper introduces an efficient deep neural network for image denoising that classifies pixels based on local gradients and employs class-specific convolutions, significantly reducing computational costs while maintaining high denoising performance.

Contribution

It proposes a novel class-specific convolution layer and a divide-and-conquer scheme for efficient, pattern-specific image denoising with reduced computation.

Findings

Reduces computational costs compared to state-of-the-art methods.

Maintains comparable denoising performance on public datasets.

Effective for specific textures and patterns in noisy images.

Abstract

Deep neural networks have been widely used in image denoising during the past few years. Even though they achieve great success on this problem, they are computationally inefficient which makes them inappropriate to be implemented in mobile devices. In this paper, we propose an efficient deep neural network for image denoising based on pixel-wise classification. Despite using a computationally efficient network cannot effectively remove the noises from any content, it is still capable to denoise from a specific type of pattern or texture. The proposed method follows such a divide and conquer scheme. We first use an efficient U-net to pixel-wisely classify pixels in the noisy image based on the local gradient statistics. Then we replace part of the convolution layers in existing denoising networks by the proposed Class Specific Convolution layers (CSConv) which use different weights for different classes of pixels. Quantitative and qualitative evaluations on public datasets demonstrate that the proposed method can reduce the computational costs without sacrificing the performance compared to state-of-the-art algorithms.