Tutorial on Diffusion Models for Imaging and Vision

2024/03/26 by Stanley H. Chan, Chan, Stanley H. · 6 voices · 21 citations
Computer Science · Mathematics · #Artificial intelligence #Computer science #Computer vision #Data science #Diffusion #Mathematical Biology Tumor Growth #Physics #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.2403.18103

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2024/03/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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 shortcomings that were deemed difficult in the previous approaches. The goal of this tutorial is to discuss the essential ideas underlying the 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 models to solve other problems.

Cited by

• Is Your Conditional Diffusion Model Actually Denoising?
• SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
• CSMapping: Scalable Crowdsourced Semantic Mapping and Topology Inference for Autonomous Driving
• A Frequentist Statistical Introduction to Variational Inference, Autoencoders, and Diffusion Models
• Fast 3D Diffusion for Scalable Granular Media Synthesis
• DiffVolume: Diffusion Models for Volume Generation in Limit Order Books
• DiffPF: Differentiable Particle Filtering with Generative Sampling via Conditional Diffusion Models
• RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models
• prNet: Data-Driven Phase Retrieval via Stochastic Refinement
• Object-centric Denoising Diffusion Models for Physical Reasoning
• Clustering via Self-Supervised Diffusion
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach
• Unrolling Nonconvex Graph Total Variation for Image Denoising
• Optimization-Free Diffusion Model -- A Perturbation Theory Approach
• Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
• What Do You Need for Compositional Generalization in Diffusion Planning?
• Generative Diffusion Model Driven Massive Random Access in Massive MIMO Systems
• SPIEDiff: robust learning of long-time macroscopic dynamics from short-time particle simulations with quantified epistemic uncertainty
• KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems
• A hybrid proper orthogonal decomposition and diffusion framework for reduced-order forecasting of turbulent flow dynamics

Discussions

• Tutorial on diffusion models for imaging and vision [hn, 221 points, 18 comments]
• "Tutorial on Diffusion Models for Imaging and Vision" by Stanley Chan Paper: arxiv.org/abs/2403.18103 #machinelearning #diffusionmodels [bsky, 5 points, 0 comments]
• Tutorial on Diffusion Models for Imaging and Vision arxiv.org/abs/2403.18103 [bsky, 3 points, 0 comments]
• Tutorial on Diffusion Models for Imaging and Vision [hn, 2 points, 0 comments]
• Tutorial on diffusion models for imaging and vision [bsky, 0 points, 0 comments]
• 👀 arxiv.org/abs/2403.18103 [bsky, 0 points, 0 comments]

Related

• Diffusion Models: A Comprehensive Survey of Methods and Applications
• Efficient Diffusion Models: A Comprehensive Survey From Principles to Practices
• Understanding and contextualising diffusion models
• Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices
• Efficient Diffusion Models: A Survey