Batch Denoising via Blahut-Arimoto
Abstract
In this work, we propose to solve batch denoising using Blahut-Arimoto algorithm (BA). Batch denoising via BA (BDBA), similar to Deep Image Prior (DIP), is based on an untrained score-based generative model. Theoretical results show that our denoising estimation is highly likely to be close to the best result. Experimentally, we show that BDBA outperforms DIP significantly.
Cite
Text
Li and Guyot. "Batch Denoising via Blahut-Arimoto." NeurIPS 2022 Workshops: SBM, 2022.Markdown
[Li and Guyot. "Batch Denoising via Blahut-Arimoto." NeurIPS 2022 Workshops: SBM, 2022.](https://mlanthology.org/neuripsw/2022/li2022neuripsw-batch/)BibTeX
@inproceedings{li2022neuripsw-batch,
title = {{Batch Denoising via Blahut-Arimoto}},
author = {Li, Qing and Guyot, Cyril},
booktitle = {NeurIPS 2022 Workshops: SBM},
year = {2022},
url = {https://mlanthology.org/neuripsw/2022/li2022neuripsw-batch/}
}