1 code implementation • 29 Mar 2024 • Hu Gao, Depeng Dang
The CLGF module is composed of two branches: the global branch captures long-range dependency features via a selective state spaces model, while the local branch employs simplified channel attention to model local connectivity, thereby reducing local pixel forgetting and channel redundancy.
Ranked #1 on Deblurring on RealBlur-R (trained on GoPro)
1 code implementation • 6 Sep 2023 • Hu Gao, Depeng Dang
Image restoration aims to recover the high-quality images from their degraded observations.
Ranked #1 on Single Image Deraining on Test1200
1 code implementation • 9 May 2023 • Hu Gao, Jing Yang, Ying Zhang, Ning Wang, Jingfan Yang, Depeng Dang
Image restoration is the task of aiming to obtain a high-quality image from a corrupt input image, such as deblurring and deraining.
Ranked #1 on Image Deblurring on HIDE (trained on GOPRO)
1 code implementation • 21 Feb 2023 • Hu Gao, Zhihui Li, Depeng Dang, Ning Wang, Jingfan Yang
In this way, the feature loss and the complexity of the model is reduced, and the degradation of deep neural network during training is avoided.
1 code implementation • 21 Feb 2023 • Hu Gao, Zhihui Li, Depeng Dang, Jingfan Yang, Ning Wang
Then, we compare the prediction accuracy of the three models.
1 code implementation • 19 Feb 2023 • Hu Gao, Depeng Dang
Our main proposal is a mixed hierarchy architecture, that progressively recovers contextual information and spatial details from degraded images while we design intra-blocks to reduce system complexity.
Ranked #2 on Image Deblurring on HIDE (trained on GOPRO)