Correction by Projection: Denoising Images with Generative Adversarial Networks

03/12/2018
by   Subarna Tripathi, et al.
0

Generative adversarial networks (GANs) transform low-dimensional latent vectors into visually plausible images. If the real dataset contains only clean images, then ostensibly, the manifold learned by the GAN should contain only clean images. In this paper, we propose to denoise corrupted images by finding the nearest point on the GAN manifold, recovering latent vectors by minimizing distances in image space. We first demonstrate that given a corrupted version of an image that truly lies on the GAN manifold, we can approximately recover the latent vector and denoise the image, obtaining significantly higher quality, comparing with BM3D. Next, we demonstrate that latent vectors recovered from noisy images exhibit a consistent bias. By subtracting this bias before projecting back to image space, we improve denoising results even further. Finally, even for unseen images, our method performs better at denoising better than BM3D. Notably, the basic version of our method (without bias correction) requires no prior knowledge on the noise variance. To achieve the highest possible denoising quality, the best performing signal processing based methods, such as BM3D, require an estimate of the blur kernel.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 6

research
02/15/2017

Precise Recovery of Latent Vectors from Generative Adversarial Networks

Generative adversarial networks (GANs) transform latent vectors into vis...
research
10/09/2018

Generalized Latent Variable Recovery for Generative Adversarial Networks

The Generator of a Generative Adversarial Network (GAN) is trained to tr...
research
01/05/2022

Corrupting Data to Remove Deceptive Perturbation: Using Preprocessing Method to Improve System Robustness

Although deep neural networks have achieved great performance on classif...
research
02/12/2019

Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing

Recently, Generative Adversarial Networks (GANs) have emerged as a popul...
research
07/28/2020

Improving Generative Adversarial Networks with Local Coordinate Coding

Generative adversarial networks (GANs) have shown remarkable success in ...
research
03/17/2020

Blur, Noise, and Compression Robust Generative Adversarial Networks

Recently, generative adversarial networks (GANs), which learn data distr...
research
08/19/2021

Towards Vivid and Diverse Image Colorization with Generative Color Prior

Colorization has attracted increasing interest in recent years. Classic ...

Please sign up or login with your details

Forgot password? Click here to reset