Correction by Projection: Denoising Images with Generative Adversarial Networks

TL;DR

This paper introduces a GAN-based denoising method that projects corrupted images onto the learned manifold, effectively removing noise without prior noise knowledge, outperforming traditional techniques like BM3D.

Contribution

The paper presents a novel denoising approach using GAN manifold projection and bias correction, improving image quality without needing noise variance estimates.

Findings

Effective denoising of corrupted images via GAN manifold projection.

Bias correction enhances denoising performance.

Outperforms BM3D even on unseen images.

Abstract

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.