Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise

Authors

  • Yuqian Zhou University of Illinois at Urbana-Champaign
  • Jianbo Jiao University of Illinois at Urbana-Champaign
  • Haibin Huang Megvii Face++
  • Jue Wang University of Illinois at Urbana-Champaign
  • Thomas Huang University of Illinois at Urbana-Champaign

DOI:

https://doi.org/10.1609/aaai.v33i01.330110085

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.

Downloads

Published

2019-07-17

How to Cite

Zhou, Y., Jiao, J., Huang, H., Wang, J., & Huang, T. (2019). Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 10085-10086. https://doi.org/10.1609/aaai.v33i01.330110085

Issue

Section

Student Abstract Track