Work

Tutorial on Diffusion Models for Imaging and Vision

Year: 2024

Type: article

Abstract: The astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying principle behind these generative tools is the concept of diffusion, a particular sampling mechanism that has overcome some longstanding shortcomings in previous approaches. The goal of this tutorial is to discuss the essential ideas underlying these diffusion models. The target audience of this tutorial includes undergraduate and graduate students who are interested in doing research on diffusion models or applying these tools to solve other problems.

Source: Foundations and Trends® in Computer Graphics and Vision

DOI: 10.1561/0600000112

Author: Stanley Chan

Institution: Purdue University West Lafayette

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: National Science Foundation, Purdue University, Samsung

Awards: Collaborative Research: Robust Deep Learning in Real Physical Space: Generalization, Scalability, and Credibility, Short-Exposure Imaging through Atmospheric Turbulence using Single Photon Image Sensors, RI: Small: Learning to See Through Atmospheric Turbulence