the open
    research
    Contribute
    Back to the catalogue

    Generative AI · 2020

    Denoising Diffusion Probabilistic Models

    Ho, Jain & Abbeel

    Read the original
    Noise in, structure out.

    The idea, in brief

    Learn to reverse a gradual noising process, turning random noise into structured samples.

    From noise to structure. Understand the surprisingly simple idea behind a generation of image models.

    Read with a question in mind.

    What evidence supports the main claim? Which assumptions would change the result? What would it take to reproduce it?

    Go to the source

    This introduction is an editorial summary. The original paper contains the methods, experiments, and limitations you need for a closer look.

    arXiv: 2006.11239

    On the reading lists

    Why it matters

    Established practical diffusion training, launching the modern diffusion generation revolution.

    Condensed from the expert lists' notes.

    Inside the paper

    The problem
    Diffusion models had a tractable training setup, but convincing image samples had been difficult to demonstrate. The authors also wanted to understand how sample quality relates to likelihood and the amount of information preserved during generation.
    The idea
    The model learns to undo a fixed process that gradually corrupts images with Gaussian noise. Its practical training objective asks a neural network to predict the noise added at a chosen stage of that process.
    How it works
    • The forward process adds small amounts of Gaussian noise according to a prescribed schedule until the image approaches an unstructured noise sample.
    • During training, choose an image and a noise level, construct the corresponding noisy image directly, and teach the network to estimate the noise.
    • For generation, start with Gaussian noise and repeatedly apply learned reverse transitions, producing a less noisy image at each step.
    • The authors connect this parameterization to denoising score matching and examine the intermediate steps as a form of progressive lossy decoding.
    What it showed
    The paper reports an FID of 3.17 on unconditional CIFAR10 and shows samples on several image datasets. It also finds that good sample quality does not by itself imply competitive likelihood, a distinction visible in its compression analysis.
    Read it for
    Read Sections 2 and 3.2 alongside Algorithms 1 and 2 to follow training and sampling, then look at Section 4 and its samples. The detailed variational derivation can be skimmed on a first pass and revisited for the objective’s weighting.

    Written in our own words from the paper itself. A draft the editors have not yet reviewed.

    Reading it

    Difficulty: Advanced

    Read this first: Auto-Encoding Variational Bayes; probability.

    The record

    First released
    2020 (from arXiv 2006.11239)
    Citations
    36,409 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.738 · computed rank 40 · consensus 0.96, must-read 1, citations percentile 1 (2020s · generative-models), awards 0, existing lists 0. Method

    Editor's notes

    • Readability check: pass: The diffusion model paper learners should start from. (AI draft (Claude), not yet reviewed, 2026-10-29)

    This paper's reading-list entry has its rank, release date and sources in full.

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.