GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions

Image restoration in adverse weather conditions is a difficult task in computer vision. In this paper, we propose a novel transformer-based framework called GridFormer which serves as a backbone for image restoration under adverse weather conditions. GridFormer is designed in a grid structure using...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer vision Vol. 132; no. 10; pp. 4541 - 4563
Main Authors: Wang, Tao, Zhang, Kaihao, Shao, Ziqian, Luo, Wenhan, Stenger, Bjorn, Lu, Tong, Kim, Tae-Kyun, Liu, Wei, Li, Hongdong
Format: Journal Article
Language:English
Published: New York Springer US 01.10.2024
Springer
Springer Nature B.V
Subjects:
Artificial Intelligence
Attention
Computer Imaging
Computer Science
Computer vision
Design
Electric transformers
Image enhancement
Image processing
Image Processing and Computer Vision
Image restoration
Machine vision
Pattern Recognition
Pattern Recognition and Graphics
Source code
Vision
Weather
Image dehazing
Image deraining
Transformer
Image restoration
Multi-weather restoration
Attention
ISSN:0920-5691, 1573-1405
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Image restoration in adverse weather conditions is a difficult task in computer vision. In this paper, we propose a novel transformer-based framework called GridFormer which serves as a backbone for image restoration under adverse weather conditions. GridFormer is designed in a grid structure using a residual dense transformer block, and it introduces two core designs. First, it uses an enhanced attention mechanism in the transformer layer. The mechanism includes stages of the sampler and compact self-attention to improve efficiency, and a local enhancement stage to strengthen local information. Second, we introduce a residual dense transformer block (RDTB) as the final GridFormer layer. This design further improves the network’s ability to learn effective features from both preceding and current local features. The GridFormer framework achieves state-of-the-art results on five diverse image restoration tasks in adverse weather conditions, including image deraining, dehazing, deraining & dehazing, desnowing, and multi-weather restoration. The source code and pre-trained models will be released.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-024-02056-0