Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise

  • 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

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.

Published
2019-07-17
Section
Student Abstract Track