# Learning Deep Image Priors for Blind Image Denoising

## TL;DR

This paper introduces a novel blind image denoising method that learns domain-invariant feature and pixel priors through adversarial training, effectively handling various noise levels and improving both quantitative and perceptual quality.

## Contribution

It proposes a dual-prior approach based on domain alignment using adversarial training, enhancing robustness and perceptual quality in blind image denoising.

## Key findings

- Effective on synthetic and real-world noisy images
- Feature prior reduces noise level discrepancy
- Pixel prior improves perceptual quality

## Abstract

Image denoising is the process of removing noise from noisy images, which is an image domain transferring task, i.e., from a single or several noise level domains to a photo-realistic domain. In this paper, we propose an effective image denoising method by learning two image priors from the perspective of domain alignment. We tackle the domain alignment on two levels. 1) the feature-level prior is to learn domain-invariant features for corrupted images with different level noise; 2) the pixel-level prior is used to push the denoised images to the natural image manifold. The two image priors are based on $\mathcal{H}$-divergence theory and implemented by learning classifiers in adversarial training manners. We evaluate our approach on multiple datasets. The results demonstrate the effectiveness of our approach for robust image denoising on both synthetic and real-world noisy images. Furthermore, we show that the feature-level prior is capable of alleviating the discrepancy between different level noise. It can be used to improve the blind denoising performance in terms of distortion measures (PSNR and SSIM), while pixel-level prior can effectively improve the perceptual quality to ensure the realistic outputs, which is further validated by subjective evaluation.