article2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Jun 1, 2022Closed access

The Devil Is in the Details: Window-based Attention for Image Compression

RZRenjie ZouCSChunfeng SongZZZhaoxiang Zhang

University of Chinese Academy of Sciences · Centre for Artificial Intelligence and Robotics

Indexed incrossref

Abstract

Learned image compression methods have exhibited superior rate-distortion performance than classical image compression standards. Most existing learned image compression models are based on Convolutional Neural Networks (CNNs). Despite great contributions, a main drawback of CNN based model is that its structure is not designed for capturing local redundancy, especially the nonrepetitive textures, which severely affects the reconstruction quality. Therefore, how to make full use of both global structure and local texture becomes the core problem for learning-based image compression. Inspired by recent progresses of Vision Transformer (ViT) and Swin Transformer, we found that combining the local-aware attention…

Citation impact

264
total citations
FWCI
14.40
Percentile
100%
References
58
Citations per year

Authors

3

Topics & keywords

Topics
Keywords
  • Computer science
  • Encoder
  • Artificial intelligence
  • Image compression
  • Transformer
  • Convolutional neural network
  • Redundancy (engineering)
  • Computer vision
No related works found for this paper.

Funding