Towards a General-Purpose Zero-Shot Synthetic Low-Light Image and Video Pipeline

J. Lin

C. Morris

R. Lin

F. Zhang

D. Bull

N. Anantrasirichai

Funders: MyWorld Strength in Places, British Broadcasting Coorporation (BBC)


PDF ArXiv Code
Thumbnail

Abstract

Low-light conditions pose significant challenges for both human and machine annotation. This in turn has led to a lack of research into machine understanding for low-light images and (in particular) videos. A common approach is to apply annotations obtained from high quality datasets to synthetically created low light versions. In addition, these approaches are often limited through the use of unrealistic noise models. In this paper, we propose a new Degradation Estimation Network (DEN), which synthetically generates realistic standard RGB (sRGB) noise without the requirement for camera metadata. This is achieved by estimating the parameters of physics-informed noise distributions, trained in a self-supervised manner. This zero-shot approach allows our method to generate synthetic noisy content with a diverse range of realistic noise characteristics, unlike other methods which focus on recreating the noise characteristics of the training data. We evaluate our proposed synthetic pipeline using various methods trained on its synthetic data for typical low-light tasks including synthetic noise replication, video enhancement, and object detection, showing improvements of up to 24% KLD, 21% LPIPS, and 62% AP50-95, respectively.

Citation

If you use our work in your research, please cite using the following BibTeX entry:

@inproceedings{lin2025den,
  author = {Lin, Joanne and Morris, Crispian and Lin, Ruirui and Zhang, Fan and Bull, David and Anantrasirichai, Nantheera},
  title = {Towards a General-Purpose Zero-Shot Synthetic Low-Light Image and Video Pipeline},
  year = {2025},
  isbn = {9798400720604},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3746278.3759376},
  doi = {10.1145/3746278.3759376},
  booktitle = {Proceedings of the 3rd International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice},
  pages = {3–11},
  numpages = {9},
  keywords = {synthetic data, low-light, degradations, general-purpose, zero-shot, self-supervised},
  location = {Ireland},
  series = {McGE '25}
}