Pith. sign in

REVIEW 5 cited by

Generative Modelling With Inverse Heat Dissipation

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 2206.13397 v7 pith:KB4KUBCU submitted 2022-06-21 cs.CV cs.LGstat.ML

Severi Rissanen , Markus Heinonen , Arno Solin This is my paper · ORCID
classification cs.CVcs.LGstat.ML
keywords diffusionimagesmodelsheatmodelcoarse-to-fineequationgenerative
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While diffusion models have shown great success in image generation, their noise-inverting generative process does not explicitly consider the structure of images, such as their inherent multi-scale nature. Inspired by diffusion models and the empirical success of coarse-to-fine modelling, we propose a new diffusion-like model that generates images through stochastically reversing the heat equation, a PDE that locally erases fine-scale information when run over the 2D plane of the image. We interpret the solution of the forward heat equation with constant additive noise as a variational approximation in the diffusion latent variable model. Our new model shows emergent qualitative properties not seen in standard diffusion models, such as disentanglement of overall colour and shape in images. Spectral analysis on natural images highlights connections to diffusion models and reveals an implicit coarse-to-fine inductive bias in them.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 11 citations worldwide. 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. StrideDiffusion: Accelerating Diffusion Models for Time-series Generation

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A training-free sampler that adapts diffusion denoising strides to spectral band activity, cutting inference steps from 500-1000 to 14-66 with mostly comparable quality.

  3. Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Fine-tuning a pretrained diffusion model with a GAN objective and most weights frozen yields a one-step generator that matches or beats prior distillation methods on several datasets.

  4. 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.

  5. Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution

    cs.CV 2026-07 reject novelty 4.0 of 10

    DDR-SR routes each real-world low-resolution image to one of two diffusion experts based on a high-frequency-loss difficulty score, using a low-compression VAE for hard images and a high-compression VAE for easy image...

Pith tools