Affiliation:
1. School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430081, China
2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology, Wuhan 430081, China
Abstract
Low-light conditions severely degrade the captured image quality with few details, while deep learning approaches are trending towards low-light image enhancement (LLIE) due to their superior performance. However, few methods face the challenges of lower dynamic range and greater noise from extremely low-light directly. Existing methods for extremely low-light enhancement are end-to-end, requiring RAW data as input. Meanwhile, they often lack the potential for real-time mobile deployment owing to the high model complexity. In this paper, we introduce the image-to-curve transformation to ELLIE for the first time and present a Lightweight Image-to-curve MaPpIng moDel for ELLIE (LIMPID). Compared with existing image-to-curve mapping methods, the proposed module is constructed for a wider dynamic range according to the light scattering model. Furthermore, we propose a new pyramid fusion strategy based on Laplacian and Gaussian. This strategy attempts to achieve dynamic fusion of multi-scale images via learnable fusion weight parameters. Specifically, LIMPID consists of a low-resolution dense CNN network stream and a full-resolution guidance stream. First, the curve generation and refinement are achieved in the low-resolution stream constructed on a light scattering model. Then, the curves are up-sampled to full resolution via bilateral grid cells. Finally, the enhanced result is obtained through dynamically adapted multi-scale pyramid fusion. Experimental results show that our method is competitive with existing state-of-the-art methods in terms of performance.
Funder
Natural Science Foundation of China
Natural Science Foundation of Hubei Province
Subject
Radiology, Nuclear Medicine and imaging,Instrumentation,Atomic and Molecular Physics, and Optics
Reference49 articles.
1. Lightening Network for Low-Light Image Enhancement;Wang;IEEE Trans. Image Process.,2020
2. Luminance-aware Pyramid Network for Low-light Image Enhancement;Li;IEEE Trans. Multimed.,2020
3. Zhang, Y., Zhang, J., and Guo, X. (2019, January 21–25). Kindling the darkness: A practical low-light image enhancer. Proceedings of the ACMMM, Nice, France.
4. Fan, M., Wang, W., Yang, W., and Liu, J. (2020, January 12–16). Integrating semantic segmentation and retinex model for low-light image enhancement. Proceedings of the ACMMM, Seattle, WA, USA.
5. Star: A structure and texture aware retinex model;Xu;IEEE Trans. Image Process.,2020