Everything about Diffusion model
Technique for the generative modeling of a continuous probability distribution
In machine learning, diffusion models, also known as diffusion-based generative models or score-based generative models, are a class of latent variable generative models. A diffusion model consists of two major components: the forward diffusion process, and the reverse sampling process. The goal of diffusion models is to learn a diffusion process for a given dataset, such that the process can generate new elements that are distributed similarly as the original dataset. A diffusion model models data as generated by a diffusion process, whereby a new datum performs a random walk with drift through the space of all possible data. A trained diffusion model can be sampled in many ways, with different efficiency and quality. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Diffusion modelA 5-minute orientation
- Skim a recent paper: Diffusion Models in Vision: A SurveyInfluential work since 2022
- Pick up a classic book: The over-land along-wind dispersion (OLAD) field experimentThe most-reprinted book on the subject
- Read the landmark paper: Brownian motion in a field of force and the diffusion model of chemical reactionsCited 8,034 times
- Go sideways: Discrete diffusion modelA closely related topic
- Go sideways: Latent diffusion modelA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🏆 Landmark papers (most cited)
Brownian motion in a field of force and the diffusion model of chemical reactions
In Vivo Facilitated Diffusion Model
Relativistic diffusion model
A Dual‐Process Diffusion Model
Solution-diffusion-imperfection model revised
A diffusion hydrodynamic model (DHM)
Diffusion of water in rhyolite glass: diffusion–reaction model
Diffusion Model for Insect Dispersal
🆕 Influential since 2022
Diffusion Models in Vision: A Survey
Diffusion Models: A Comprehensive Survey of Methods and Applications
T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models
Diffusion models in medical imaging: A comprehensive survey
SRDiff: Single image super-resolution with diffusion probabilistic models
📚 Books worth reading
- 📕The over-land along-wind dispersion (OLAD) field experimentAir Resources Laboratory (U.S.) · 2000
The mathematics of diffusionJohn Crank · 1956- 📕Addendum to TUPOS--incorporation of a hesitant plume algorithmD. Bruce Turner · 1986
- 📕TUPOS-PD. Bruce Turner · 1986
- 📕TRIAD, a puff-trajectory model for reactive gas dispersion with application to UF₆ releases into the atmosphereB. B Hicks · 1989
Diffusion Processes In Advanced Technological MaterialsDevendra Gupta · 2004
Air pollution modeling and its application XSven-Erik Gryning · 1994- 📕A three-dimensional method-of-characteristics solute- transport model (MOC3D)Leonard F. Konikow · 1996
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Discrete diffusion model In machine learning, discrete diffusion models are a class of diffusion models, which themselves are a class of latent variable generative models. Each…
- Latent diffusion model The latent diffusion model (LDM) is a diffusion model architecture developed by the CompVis (Computer Vision & Learning) group at LMU Munich. Introduced…
- Variational autoencoder In machine learning, a variational autoencoder (VAE) is an artificial neural network architecture introduced by Diederik P. Kingma and Max Welling in 2013…
- Generative adversarial network A generative adversarial network (GAN) is a class of machine learning frameworks and a prominent framework for approaching generative AI. The concept was…
- Gaussian function In mathematics, a Gaussian function, often simply referred to as a Gaussian, is a function of the base form f(x)=exp(−x2) and with parametric extension…
- Deep image prior Deep image prior is a type of convolutional neural network used to enhance a given image with no prior training data other than the image itself. A neural…
- Doob's h-transform In mathematics, more specifically in stochastics, Doob's h-transform is a method to transform a Markov process into a new Markov process, which exhibits…
- Flow-based generative model A flow-based generative model is a generative model used in machine learning that explicitly models a probability distribution by leveraging normalizing…