Learning Generalizable Latent Representations for Novel Degradations in Super Resolution

TL;DR

This paper introduces a method to learn a latent space of image degradations that generalizes to unseen, real-world degradations, enabling better training data generation for blind super-resolution models.

Contribution

It proposes a novel latent representation learning approach that generalizes from handcrafted to real-world degradations, improving blind super-resolution performance.

Findings

Effective in handling novel degradations in synthetic datasets

Improves super-resolution quality on real-world images

Outperforms existing blind SR methods

Abstract

Typical methods for blind image super-resolution (SR) focus on dealing with unknown degradations by directly estimating them or learning the degradation representations in a latent space. A potential limitation of these methods is that they assume the unknown degradations can be simulated by the integration of various handcrafted degradations (e.g., bicubic downsampling), which is not necessarily true. The real-world degradations can be beyond the simulation scope by the handcrafted degradations, which are referred to as novel degradations. In this work, we propose to learn a latent representation space for degradations, which can be generalized from handcrafted (base) degradations to novel degradations. The obtained representations for a novel degradation in this latent space are then leveraged to generate degraded images consistent with the novel degradation to compose paired training data for SR model. Furthermore, we perform variational inference to match the posterior of degradations in latent representation space with a prior distribution (e.g., Gaussian distribution). Consequently, we are able to sample more high-quality representations for a novel degradation to augment the training data for SR model. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness and advantages of our method for blind super-resolution with novel degradations.