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.
1 code implementation • CVPR 2023 • Jinghao Zhang, Jie Huang, Mingde Yao, Zizheng Yang, Hu Yu, Man Zhou, Feng Zhao
Learning to leverage the relationship among diverse image restoration tasks is quite beneficial for unraveling the intrinsic ingredients behind the degradation.
no code implementations • CVPR 2022 • Zhihong Pan, Baopu Li, Dongliang He, Mingde Yao, Wenhao Wu, Tianwei Lin, Xin Li, Errui Ding
Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel.
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 • 25 May 2021 • Wenhao Wu, Yuxiang Zhao, Yanwu Xu, Xiao Tan, Dongliang He, Zhikang Zou, Jin Ye, YingYing Li, Mingde Yao, ZiChao Dong, Yifeng Shi
Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition.
Ranked #6 on Action Recognition on ActivityNet