Dancing Under the Stars: Video Denoising in Starlight

Kristina Monakhova, Stephan R. Richter, Laura Waller, Vladlen Koltun; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 16241-16251

Abstract


Imaging in low light is extremely challenging due to low photon counts. Using sensitive CMOS cameras, it is currently possible to take videos at night under moonlight (0.05-0.3 lux illumination). In this paper, we demonstrate photorealistic video under starlight (no moon present, <0.001 lux) for the first time. To enable this, we develop a GAN-tuned physics-based noise model to more accurately represent camera noise at the lowest light levels. Using this noise model, we train a video denoiser using a combination of simulated noisy video clips and real noisy still images. We capture a 5-10 fps video dataset with significant motion at approximately 0.6-0.7 millilux with no active illumination. Comparing against alternative methods, we achieve improved video quality at the lowest light levels, demonstrating photorealistic video denoising in starlight for the first time.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Monakhova_2022_CVPR, author = {Monakhova, Kristina and Richter, Stephan R. and Waller, Laura and Koltun, Vladlen}, title = {Dancing Under the Stars: Video Denoising in Starlight}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {16241-16251} }