Work

An overview of diffusion models for generative artificial intelligence

Year: 2024

Type: preprint

Abstract: This article provides a mathematically rigorous introduction to denoising diffusion probabilistic models (DDPMs), sometimes also referred to as diffusion probabilistic models or diffusion models, for generative artificial intelligence. We provide a detailed basic mathematical framework for DDPMs and explain the main ideas behind training and generation procedures. In this overview article we also review selected extensions and improvements of the basic framework from the literature such as improved DDPMs, denoising diffusion implicit models, classifier-free diffusion guidance models, and latent diffusion models.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2412.01371

Authors: Gallon, Davide, Jentzen, Arnulf, von Wurstemberger, Philippe

Institutions: University of Münster, ETH Zurich, Chinese University of Hong Kong, Shenzhen

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Deutsche Forschungsgemeinschaft, National Natural Science Foundation of China

Awards: G1652504919, G233855633, EXC 2044: Mathematik Münster: Dynamik – Geometrie – Struktur, G6938060324

OpenAlex ID: W4405034225

Cites:

Cited by:

Related to: 10