REVIEW 4 cited by
Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models
Not yet reviewed by Pith; the record is open.
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
Signed reviews
read the original abstract
Generative models based on denoising diffusion techniques have led to an unprecedented increase in the quality and diversity of imagery that is now possible to create with neural generative models. However, most contemporary state-of-the-art methods are derived from a standard isotropic Gaussian formulation. In this work we examine the situation where non-isotropic Gaussian distributions are used. We present the key mathematical derivations for creating denoising diffusion models using an underlying non-isotropic Gaussian noise model. We also provide initial experiments with the CIFAR-10 dataset to help verify empirically that this more general modeling approach can also yield high-quality samples.
Forward citations
Cited by 4 Pith papers
-
Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality
A diffusion model's training loss and output quality depend measurably on which pseudorandom orbit supplies its randomness, even after marginal-statistics control.
-
A Fourier Space Perspective on Diffusion Models
EqualSNR, a diffusion forward process that corrupts every Fourier frequency at the same rate, improves high-frequency generation quality while matching DDPM's FID on standard image benchmarks.
-
Robust Graph Learning Against Adversarial Evasion Attacks via Prior-Free Diffusion-Based Structure Purification
DiffSP purifies attacked graphs by learning the clean graph distribution with a discrete diffusion model and reports consistent accuracy improvements over baselines on nine datasets and nine evasion attacks.
-
Generalized Score Matching: Bridging $f$-Divergence and Statistical Estimation Under Correlated Noise
The paper's central theorem, linking the covariance-gradient of f-divergence to a generalized Fisher information, is off by a missing factor (1-alpha_t) inherited from a flawed heat-equation lemma.
Discussion (0). Continue with ORCID to comment.