Journal
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
Volume -, Issue -, Pages 4419-4428Publisher
IEEE
DOI: 10.1109/ICCV48922.2021.00440
Keywords
-
Funding
- Ministry of Science and Technology China (MOST) [2018AAA0102200]
- Natural Science Foundation China (NSFC) [61827814]
- Shenzhen Science and Technology Innovation Commission (SZSTI) [JCYJ20190808153619413]
Ask authors/readers for more resources
The study proposes an adaptive unfolding total variation network (UTVNet) to enhance real low-light images by approximating noise level and learning noise level map, leading to superior performance over state-of-the-art methods.
Real-world low-light images suffer from two main degradations, namely, inevitable noise and poor visibility. Since the noise exhibits different levels, its estimation has been implemented in recent works when enhancing low-light images from raw Bayer space. When it comes to sRGB color space, the noise estimation becomes more complicated due to the effect of the image processing pipeline. Nevertheless, most existing enhancing algorithms in sRGB space only focus on the low visibility problem or suppress the noise under a hypothetical noise level, leading them impractical due to the lack of robustness. To address this issue, we propose an adaptive unfolding total variation network (UTVNet), which approximates the noise level from the real sRGB low-light image by learning the balancing parameter in the model-based denoising method with total variation regularization. Meanwhile, we learn the noise level map by unrolling the corresponding minimization process for providing the inferences of smoothness and fidelity constraints. Guided by the noise level map, our UTVNet can recover finer details and is more capable to suppress noise in real captured low-light scenes. Extensive experiments on real-world low-light images clearly demonstrate the superior performance of UTVNet over state-of-the-art methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available