User: Guest  Login
Title:

Dual-domain strip attention for image restoration

Document type:
Zeitschriftenaufsatz
Author(s):
Cui, Yuning; Knoll, Alois
Abstract:
Image restoration aims to reconstruct a latent high-quality image from a degraded observation. Recently, the usage of Transformer has significantly advanced the state-of-the-art performance of various image restoration tasks due to its powerful ability to model long-range dependencies. However, the quadratic complexity of self-attention hinders practical applications. Moreover, sufficiently leveraging the huge spectral disparity between clean and degraded image pairs can also be conducive to ima...     »
Keywords:
Image restoration, Dual-domain learning, Efficient network
Journal title:
Neural Networks
Year:
2023
Fulltext / DOI:
doi:10.1016/j.neunet.2023.12.003
WWW:
https://www.sciencedirect.com/science/article/pii/S0893608023006974
Print-ISSN:
0893-6080
 BibTeX