Rendering Nighttime Image Via Cascaded Color and Brightness Compensation
Not on the map. Why?
Abstract (arXiv)
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 white balance and tone mapping annotated by expert professionals. Meanwhile, to best capture the characteristics of nighttime illumination light sources, we develop the CBUnet, 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. The code and relevant materials are avaiable on our website: https://njuvision.github.io/CBUnet.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 40 references that are in the map. First posted on arXiv 19 Apr 2022.
Builds on
15 of 40 references.
References · 15
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
- 2016Learning Deep Embeddings with Histogram Losscited by 52
- 2020NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Resultscited by 51
- 2020AWNet: Attentive Wavelet Network for Image ISPcited by 38
- 2016Fast Fourier Color Constancycited by 37
- 2015Convolutional Color Constancycited by 36
- 2019Deep Tone Mapping Operator for High Dynamic Range Imagescited by 26
- 2015Single and Multiple Illuminant Estimation Using Convolutional Neural Networkscited by 12
- 2019HighEr-Resolution Network for Image Demosaicing and Enhancingcited by 11
3 more
- 2020The Cube++ Illumination Estimation Datasetcited by 10
- 2021Unpaired Learning for High Dynamic Range Image Tone Mappingcited by 10
- 2019W-Net: Two-stage U-Net with misaligned data for raw-to-RGB mappingcited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.