跳到主要导航 跳到搜索 跳到主要内容

Efficient Deep Image Denoising via Class Specific Convolution

  • Lu Xu
  • , Jiawei Zhang
  • , Xuanye Cheng
  • , Feng Zhang
  • , Xing Wei
  • , Jimmy Ren
  • Chinese University of Hong Kong
  • SenseTime Group Limited
  • Shanghai Jiao Tong University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

13 引用 (Scopus)

摘要

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.

源语言英语
主期刊名35th AAAI Conference on Artificial Intelligence, AAAI 2021
出版商Association for the Advancement of Artificial Intelligence
页3039-3046
页数8
ISBN(电子版)9781713835974
DOI
出版状态已出版 - 2021
活动35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online
期限: 2 2月 2021 → 9 2月 2021

丛书

姓名35th AAAI Conference on Artificial Intelligence, AAAI 2021
卷4A

会议

会议35th AAAI Conference on Artificial Intelligence, AAAI 2021
市Virtual, Online
时期2/02/21 → 9/02/21

学术指纹

探究 'Efficient Deep Image Denoising via Class Specific Convolution' 的科研主题。它们共同构成独一无二的学术指纹。

引用此