Non-Parametric Sensor Noise Modeling and Synthesis
Abstract
We introduce a novel non-parametric sensor noise model that directly constructs probability mass functions per intensity level from captured images. We show that our noise model provides a more accurate fit to real sensor noise than existing models. We detail the capture procedure for deriving our non-parametric noise model and introduce an interpolation method that reduces the number of ISOs levels that need to be captured. In addition, we propose a method to synthesize noise on existing noisy images when noise-free images are not available. Our noise model is straightforward to calibrate and provides notable improvements over competing noise models on downstream tasks.
Cite
Text
Mosleh et al. "Non-Parametric Sensor Noise Modeling and Synthesis." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72691-0_5Markdown
[Mosleh et al. "Non-Parametric Sensor Noise Modeling and Synthesis." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/mosleh2024eccv-nonparametric/) doi:10.1007/978-3-031-72691-0_5BibTeX
@inproceedings{mosleh2024eccv-nonparametric,
title = {{Non-Parametric Sensor Noise Modeling and Synthesis}},
author = {Mosleh, Ali and Zhao, Luxi and Singh, Atin Vikram and Han, Jaeduk and Punnappurath, Abhijith and Brubaker, Marcus A and Choe, Jihwan and Brown, Michael S},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72691-0_5},
url = {https://mlanthology.org/eccv/2024/mosleh2024eccv-nonparametric/}
}