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

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 67
  • Download : 0
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.
Publisher
SPRINGER
Issue Date
2024-10
Language
English
Article Type
Article
Citation

INTERNATIONAL JOURNAL OF COMPUTER VISION, v.132, no.10, pp.4541 - 4563

ISSN
0920-5691
DOI
10.1007/s11263-024-02056-0
URI
http://hdl.handle.net/10203/323466
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0