TY - GEN
T1 - Focal Network for Image Restoration
AU - Cui, Yuning
AU - Ren, Wenqi
AU - Cao, Xiaochun
AU - Knoll, Alois
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Image restoration aims to reconstruct a sharp image from its degraded counterpart, which plays an important role in many fields. Recently, Transformer models have achieved promising performance on various image restoration tasks. However, their quadratic complexity remains an intractable issue for practical applications. The aim of this study is to develop an efficient and effective framework for image restoration. Inspired by the fact that different regions in a corrupted image always undergo degradations in various degrees, we propose to focus more on the important areas for reconstruction. To this end, we introduce a dual-domain selection mechanism to emphasize crucial information for restoration, such as edge signals and hard regions. In addition, we split high-resolution features to insert multi-scale receptive fields into the network, which improves both efficiency and performance. Finally, the proposed network, dubbed FocalNet, is built by incorporating these designs into a U-shaped backbone. Extensive experiments demonstrate that our model achieves state-of-the-art performance on ten datasets for three tasks, including single-image defocus deblurring, image dehazing, and image desnowing. Our code is available at https://github.com/c-yn/FocalNet.
AB - Image restoration aims to reconstruct a sharp image from its degraded counterpart, which plays an important role in many fields. Recently, Transformer models have achieved promising performance on various image restoration tasks. However, their quadratic complexity remains an intractable issue for practical applications. The aim of this study is to develop an efficient and effective framework for image restoration. Inspired by the fact that different regions in a corrupted image always undergo degradations in various degrees, we propose to focus more on the important areas for reconstruction. To this end, we introduce a dual-domain selection mechanism to emphasize crucial information for restoration, such as edge signals and hard regions. In addition, we split high-resolution features to insert multi-scale receptive fields into the network, which improves both efficiency and performance. Finally, the proposed network, dubbed FocalNet, is built by incorporating these designs into a U-shaped backbone. Extensive experiments demonstrate that our model achieves state-of-the-art performance on ten datasets for three tasks, including single-image defocus deblurring, image dehazing, and image desnowing. Our code is available at https://github.com/c-yn/FocalNet.
UR - http://www.scopus.com/inward/record.url?scp=85185868462&partnerID=8YFLogxK
U2 - 10.1109/ICCV51070.2023.01195
DO - 10.1109/ICCV51070.2023.01195
M3 - Conference contribution
AN - SCOPUS:85185868462
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 12955
EP - 12965
BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Y2 - 2 October 2023 through 6 October 2023
ER -