A Comprehensive Survey on Diffusion Models and Their Applications

TL;DR

This paper provides a comprehensive overview of Diffusion Models, detailing their theoretical foundations, algorithmic innovations, and diverse applications across multiple fields to facilitate broader understanding and adoption.

Contribution

It offers the first broad survey covering theoretical, algorithmic, and application aspects of Diffusion Models across various disciplines.

Findings

Diffusion Models are effective in generating high-quality samples.

They have diverse applications in image processing, speech synthesis, and healthcare.

The survey identifies emerging trends and future research directions.

Abstract

Diffusion Models are probabilistic models that create realistic samples by simulating the diffusion process, gradually adding and removing noise from data. These models have gained popularity in domains such as image processing, speech synthesis, and natural language processing due to their ability to produce high-quality samples. As Diffusion Models are being adopted in various domains, existing literature reviews that often focus on specific areas like computer vision or medical imaging may not serve a broader audience across multiple fields. Therefore, this review presents a comprehensive overview of Diffusion Models, covering their theoretical foundations and algorithmic innovations. We highlight their applications in diverse areas such as media quality, authenticity, synthesis, image transformation, healthcare, and more. By consolidating current knowledge and identifying emerging trends, this review aims to facilitate a deeper understanding and broader adoption of Diffusion Models and provide guidelines for future researchers and practitioners across diverse disciplines.