Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise

Yuqian Zhou, Jianbo Jiao, Haibin Huang, Jue Wang, Thomas S. Huang

AAAI 2019 pp. 10085-10086

doi:10.1609/AAAI.V33I01.330110085 /aaai/2019/zhou2019aaai-adaptation/

Abstract

Discriminative learning based denoising model trained with Additive White Gaussian Noise (AWGN) performs well on synthesized noise. However, realistic noise can be spatialvariant, signal-dependent and a mixture of complicated noises. In this paper, we explore multiple strategies for applying an AWGN-based denoiser to realistic noise. Specifically, we trained a deep network integrating noise estimating and denoiser with mixed Gaussian (AWGN) and Random Value Impulse Noise (RVIN). To adapt the model to realistic noises, we investigated multi-channel, multi-scale and super-resolution approaches. Our preliminary results demonstrated the effectiveness of the newly-proposed noise model and adaptation strategies.

PDF AAAI Semantic Scholar

Cite

Text

Zhou et al. "Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.330110085

Markdown

[Zhou et al. "Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/zhou2019aaai-adaptation/) doi:10.1609/AAAI.V33I01.330110085

BibTeX

@inproceedings{zhou2019aaai-adaptation,
  title     = {{Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise}},
  author    = {Zhou, Yuqian and Jiao, Jianbo and Huang, Haibin and Wang, Jue and Huang, Thomas S.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {10085-10086},
  doi       = {10.1609/AAAI.V33I01.330110085},
  url       = {https://mlanthology.org/aaai/2019/zhou2019aaai-adaptation/}
}