High Perceptual Quality Image Denoising with a Posterior Sampling CGAN

03/06/2021
by   Guy Ohayon, et al.
14

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 (CGANs). Contrary to distortion-based regularization terms that conflict with perceptual quality, we introduce to the CGANs 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.

READ FULL TEXT

page 5

page 6

page 12

page 13

page 14

research
01/23/2021

Stochastic Image Denoising by Sampling from the Posterior Distribution

Image denoising is a well-known and well studied problem, commonly targe...
research
11/21/2022

High-Perceptual Quality JPEG Decoding via Posterior Sampling

JPEG is arguably the most popular image coding format, achieving high co...
research
07/12/2023

On the Importance of Denoising when Learning to Compress Images

Image noise is ubiquitous in photography. However, image noise is not co...
research
08/03/2017

Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss

In this paper, we introduce a new CT image denoising method based on the...
research
01/09/2023

Image Denoising: The Deep Learning Revolution and Beyond – A Survey Paper –

Image denoising (removal of additive white Gaussian noise from an image)...
research
01/14/2020

Distortion Agnostic Deep Watermarking

Watermarking is the process of embedding information into an image that ...
research
05/19/2020

One Size Fits All: Can We Train One Denoiser for All Noise Levels?

When training an estimator such as a neural network for tasks like image...

Please sign up or login with your details

Forgot password? Click here to reset