1 code implementation • 19 Oct 2023 • Mingde Yao, Ruikang Xu, Yuanshen Guan, Jie Huang, Zhiwei Xiong
To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations.
1 code implementation • ICCV 2023 • Mingde Yao, Jie Huang, Xin Jin, Ruikang Xu, Shenglong Zhou, Man Zhou, Zhiwei Xiong
Existing methods typically work well on their trained lightness conditions but perform poorly in unknown ones due to their limited generalization ability.
1 code implementation • 24 Aug 2023 • Yuanshen Guan, Ruikang Xu, Mingde Yao, Lizhi Wang, Zhiwei Xiong
Image fusion aims to generate a high-quality image from multiple images captured under varying conditions.
1 code implementation • CVPR 2023 • Ruikang Xu, Mingde Yao, Zhiwei Xiong
To overcome these two challenges, we propose a degradation-invariant alignment method and a degradation-aware training strategy to fully exploit the information within a single dual-lens pair.
no code implementations • CVPR 2023 • Ruikang Xu, Chang Chen, Jingyang Peng, Cheng Li, Yibin Huang, Fenglong Song, Youliang Yan, Zhiwei Xiong
In many computer vision applications (e. g., robotics and autonomous driving), high dynamic range (HDR) data is necessary for object detection algorithms to handle a variety of lighting conditions, such as strong glare.
no code implementations • 24 Dec 2021 • Ruikang Xu, Mingde Yao, Chang Chen, Lizhi Wang, Zhiwei Xiong
In this paper, we propose Neural Spectral Reconstruction (NeSR) to lift this limitation, by introducing a novel continuous spectral representation.
1 code implementation • 11 May 2021 • Ruikang Xu, Zeyu Xiao, Jie Huang, Yueyi Zhang, Zhiwei Xiong
Image deblurring has seen a great improvement with the development of deep neural networks.