Diffusion Models, Image Super-Resolution And Everything: A Survey

TL;DR

This survey comprehensively reviews how diffusion models have revolutionized image super-resolution by providing high-quality, realistic images, while also discussing challenges and future research directions in this rapidly evolving field.

Contribution

It offers a unified theoretical overview of diffusion models in image super-resolution and analyzes current research trends and challenges distinct from other reviews.

Findings

Diffusion models produce high-quality, realistic super-resolved images.

Current challenges include high computational costs and lack of explainability.

The survey highlights future research directions and innovative methodologies.

Abstract

Diffusion Models (DMs) have disrupted the image Super-Resolution (SR) field and further closed the gap between image quality and human perceptual preferences. They are easy to train and can produce very high-quality samples that exceed the realism of those produced by previous generative methods. Despite their promising results, they also come with new challenges that need further research: high computational demands, comparability, lack of explainability, color shifts, and more. Unfortunately, entry into this field is overwhelming because of the abundance of publications. To address this, we provide a unified recount of the theoretical foundations underlying DMs applied to image SR and offer a detailed analysis that underscores the unique characteristics and methodologies within this domain, distinct from broader existing reviews in the field. This survey articulates a cohesive understanding of DM principles and explores current research avenues, including alternative input domains, conditioning techniques, guidance mechanisms, corruption spaces, and zero-shot learning approaches. By offering a detailed examination of the evolution and current trends in image SR through the lens of DMs, this survey sheds light on the existing challenges and charts potential future directions, aiming to inspire further innovation in this rapidly advancing area.