High Perceptual Quality Image Denoising with a Posterior Sampling CGAN

Abstract

The vast work in Deep Learning (DL) has led to a leap in image denoising research. Most DL solutions for this task have chosen to put their efforts on the denoiser's architecture while maximizing distortion performance. However, distortion driven solutions lead to blurry results with sub-optimal perceptual quality, especially in immoderate noise levels. In this paper we propose a different perspective, aiming to produce sharp and visually pleasing denoised images that are still faithful to their clean sources. Formally, our goal is to achieve high perceptual quality with acceptable distortion. This is attained by a stochastic denoiser that samples from the posterior distribution, trained as a generator in the framework of conditional generative adversarial networks (CGAN). Contrary to distortion-based regularization terms that conflict with perceptual quality, we introduce to the CGAN objective a theoretically founded penalty term that does not force a distortion requirement on individual samples, but rather on their mean. We showcase our proposed method with a novel denoiser architecture that achieves the reformed denoising goal and produces vivid and diverse outcomes in immoderate noise levels.

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• The Perception-Distortion Tradeoff
• Deep multi-scale video prediction beyond mean square error
• Diversity-Sensitive Conditional Generative Adversarial Networks
• Deep Bayesian Inversion
• LIDIA: Lightweight Learned Image Denoising with Instance Adaptation
• Creating High Resolution Images with a Latent Adversarial Generator
• Variational Inference for Computational Imaging Inverse Problems

Cited by in corpus (3)

• A Theory of the Distortion-Perception Tradeoff in Wasserstein Space
• SNIPS: Solving Noisy Inverse Problems Stochastically
• About exchanging expectation and supremum for conditional Wasserstein GANs