Pith. sign in

REVIEW 4 cited by

Blurring Diffusion Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2209.05557 v3 pith:37KLJGTD submitted 2022-09-12 cs.LG cs.CVstat.ML

Emiel Hoogeboom , Tim Salimans This is my paper · ORCID
classification cs.LGcs.CVstat.ML
keywords diffusionblurringdissipationgaussianheatmodelsdenoisinginverse
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, Rissanen et al., (2022) have presented a new type of diffusion process for generative modeling based on heat dissipation, or blurring, as an alternative to isotropic Gaussian diffusion. Here, we show that blurring can equivalently be defined through a Gaussian diffusion process with non-isotropic noise. In making this connection, we bridge the gap between inverse heat dissipation and denoising diffusion, and we shed light on the inductive bias that results from this modeling choice. Finally, we propose a generalized class of diffusion models that offers the best of both standard Gaussian denoising diffusion and inverse heat dissipation, which we call Blurring Diffusion Models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Energy-Guided Flow Matching

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Energy-Guided Flow Matching replaces the fixed clean endpoint with a sample-adaptive heat-kernel-filtered endpoint, yielding coarse-to-fine generation, better ImageNet FID, and faster convergence.

  2. S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domain

    cs.IR 2024-12 conditional novelty 6.0 of 10

    S-Diff defines a forward diffusion process in the graph spectral domain, using Laplacian eigenvalues to schedule per-frequency noise, and a FiLM-conditioned denoiser to recover user preferences.

  3. Insertion Based Sequence Generation with Learnable Order Dynamics

    cs.LG 2026-02 conditional novelty 5.0 of 10

    Learning per-position insertion/unmasking schedules (Kumaraswamy hazard rates) in variable-length discrete flow matching improves validity and quality on molecule generation and graph traversal relative to fixed-sched...

  4. PQD: Post-training Quantization for Efficient Diffusion Models

    cs.CV 2024-12 reject novelty 3.0 of 10

    PQD calibrates diffusion-model quantization on time steps drawn from a tuned normal distribution, reporting competitive 8-bit FID on 64x64 ImageNet but much worse 4-bit FID and no quantitative text-to-image results.

Pith tools