Efficient Deep Image Denoising via Class Specific Convolution

Authors

  • Lu Xu The Chinese University of Hong Kong
  • Jiawei Zhang SenseTime Research
  • Xuanye Cheng SenseTime Research
  • Feng Zhang SenseTime Research
  • Xing Wei School of Software Engineering, Xi'an Jiaotong University
  • Jimmy Ren SenseTime Research Qing Yuan Research Institute, Shanghai Jiao Tong University

Keywords:

Low Level & Physics-based Vision

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.

Downloads

Published

2021-05-18

How to Cite

Xu, L., Zhang, J., Cheng, X., Zhang, F., Wei, X., & Ren, J. (2021). Efficient Deep Image Denoising via Class Specific Convolution. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3039-3046. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16412

Issue

Section

AAAI Technical Track on Computer Vision III