Rendering Nighttime Image via Cascaded Color and Brightness Compensation

Zhihao Li, Si Yi, Zhan Ma; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 897-905

Abstract


Image signal processing (ISP) is crucial for camera imaging, and neural networks (NN) solutions are extensively deployed for daytime scenes. The lack of sufficient nighttime image dataset and insights on nighttime illumination characteristics poses a great challenge for high-quality rendering using existing NN ISPs. To tackle it, we first built a high-resolution nighttime RAW-RGB (NR2R) dataset with illumination and tone mapping annotated by expert professionals. Meanwhile, to best capture the characteristics of nighttime illumination light sources, we develop the, a two-stage NN ISP to cascade the compensation of color and brightness attributes. Experiments show that our method has better visual quality compared to traditional ISP pipeline, and is ranked at the second place in the NTIRE 2022 Night Photography Rendering Challenge for two tracks by respective People's and Professional Photographer's choices.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Zhihao and Yi, Si and Ma, Zhan}, title = {Rendering Nighttime Image via Cascaded Color and Brightness Compensation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {897-905} }