TY - GEN
T1 - Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition
AU - Chen, Genggeng
AU - Dai, Kexin
AU - Yang, Kangzhen
AU - Hu, Tao
AU - Chen, Xiangyu
AU - Yang, Yongqing
AU - Dong, Wei
AU - Wu, Peng
AU - Zhang, Yanning
AU - Yan, Qingsen
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - In real-world scenarios, due to a series of image degradations, obtaining high-quality, clear content photos is challenging. While significant progress has been made in synthesizing high-quality images, previous methods for image restoration and enhancement often overlooked the characteristics of different degradations. They applied the same structure to address various types of degradation, resulting in less-than-ideal restoration outcomes. Inspired by the notion that high/low frequency information is applicable to different degradations, we introduce HLNet, a Bracketing Image Restoration and Enhancement method based on high-low frequency decomposition. Specifically, we employ two modules for feature extraction: shared weight modules and non-shared weight modules. In the shared weight modules, we use SCConv to extract common features from different degradations. In the non-shared weight modules, we introduce the High-Low Frequency Decomposition Block (HLFDB), which employs different methods to handle high-low frequency information, enabling the model to address different degradations more effectively. Compared to other networks, our method takes into account the characteristics of different degradations, thus achieving higher-quality image restoration.
AB - In real-world scenarios, due to a series of image degradations, obtaining high-quality, clear content photos is challenging. While significant progress has been made in synthesizing high-quality images, previous methods for image restoration and enhancement often overlooked the characteristics of different degradations. They applied the same structure to address various types of degradation, resulting in less-than-ideal restoration outcomes. Inspired by the notion that high/low frequency information is applicable to different degradations, we introduce HLNet, a Bracketing Image Restoration and Enhancement method based on high-low frequency decomposition. Specifically, we employ two modules for feature extraction: shared weight modules and non-shared weight modules. In the shared weight modules, we use SCConv to extract common features from different degradations. In the non-shared weight modules, we introduce the High-Low Frequency Decomposition Block (HLFDB), which employs different methods to handle high-low frequency information, enabling the model to address different degradations more effectively. Compared to other networks, our method takes into account the characteristics of different degradations, thus achieving higher-quality image restoration.
UR - http://www.scopus.com/inward/record.url?scp=85206486557&partnerID=8YFLogxK
U2 - 10.1109/CVPRW63382.2024.00616
DO - 10.1109/CVPRW63382.2024.00616
M3 - 会议稿件
AN - SCOPUS:85206486557
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 6097
EP - 6107
BT - Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
PB - IEEE Computer Society
T2 - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
Y2 - 16 June 2024 through 22 June 2024
ER -