Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution

TL;DR

This paper introduces a probabilistic approach to generate diverse degradation models for unsupervised real-world image super-resolution, improving over deterministic methods by capturing complex distributions and enhancing performance on benchmark datasets.

Contribution

The paper proposes training multiple probabilistic degradation generators with a hierarchical latent variable model, improving mode coverage and super-resolution quality.

Findings

Outperforms baselines in PSNR and SSIM

Enhances robustness on unseen data

Utilizes multiple generators for better distribution modeling

Abstract

Unsupervised real world super resolution (USR) aims to restore high-resolution (HR) images given low-resolution (LR) inputs, and its difficulty stems from the absence of paired dataset. One of the most common approaches is synthesizing noisy LR images using GANs (i.e., degradation generators) and utilizing a synthetic dataset to train the model in a supervised manner. Although the goal of training the degradation generator is to approximate the distribution of LR images given a HR image, previous works have heavily relied on the unrealistic assumption that the conditional distribution is a delta function and learned the deterministic mapping from the HR image to a LR image. In this paper, we show that we can improve the performance of USR models by relaxing the assumption and propose to train the probabilistic degradation generator. Our probabilistic degradation generator can be viewed as a deep hierarchical latent variable model and is more suitable for modeling the complex conditional distribution. We also reveal the notable connection with the noise injection of StyleGAN. Furthermore, we train multiple degradation generators to improve the mode coverage and apply collaborative learning for ease of training. We outperform several baselines on benchmark datasets in terms of PSNR and SSIM and demonstrate the robustness of our method on unseen data distribution. Code is available at https://github.com/sangyun884/MSSR.