DesnowFormer: an effective transformer-based image desnowing network

Single image desnowing is an important and challenge task for lots of computer vision applications, such as visual tracking and video surveillance. Although existing deep learning-based methods have achieved promising results, most of them rely on the local deep features and neglect global relations...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE International Conference on Visual Communications and Image Processing (VCIP) pp. 1 - 5
Main Authors Zhang, Ting, Jiang, Nanfeng, Lin, Junhong, Lin, Jielian, Zhao, Tiesong
Format Conference Proceeding
LanguageEnglish
Published IEEE 13.12.2022
Subjects
Computer vision
Image Desnowing
Learning systems
Residual Spatial Attention
Semantics
Training
Transformer block
Transformers
Visual communication
Visualization
Online AccessGet full text

Cover

More Information
Summary:Single image desnowing is an important and challenge task for lots of computer vision applications, such as visual tracking and video surveillance. Although existing deep learning-based methods have achieved promising results, most of them rely on the local deep features and neglect global relationship information between the local regions. Therefore, inevitably leading to over-smooth or detail loss results. To solve this issue, we design a UNet-based end-to-end architecture for image desnowing. Specially, to better characterize global information and preserve image detail, we combine Window-based Self-Attention (WSA) transformer block with Residue Spatial Attention (RSA) to build basic unit of our network. Besides, to protect the structure of the image effectively, we also introduce a Residue Channel (RC) loss to guide high-quality image restoration. Extensive experimental results on both synthetic and real-world datasets demonstrate that the proposed model achieves new state-of-the-art results.
ISSN:2642-9357
DOI:10.1109/VCIP56404.2022.10008815