Papers › Ultra-Resolution Cascaded Diffusion Model for Gigapixel Image Synthesis in Histopathology

Ultra-Resolution Cascaded Diffusion Model for Gigapixel Image Synthesis in Histopathology

2 Dec 2023arXiv:2312.01152archive 2025-07-28

Sarah Cechnicka, Hadrien Reynaud, James Ball, Naomi Simmonds, Catherine Horsfield, Andrew Smith, Candice Roufosse, Bernhard Kainz

Diagnoses from histopathology images rely on information from both high and low resolutions of Whole Slide Images. Ultra-Resolution Cascaded Diffusion Models (URCDMs) allow for the synthesis of high-resolution images that are realistic at all magnification levels, focusing not only on fidelity but also on long-distance spatial coherency. Our model beats existing methods, improving the pFID-50k [2] score by 110.63 to 39.52 pFID-50k. Additionally, a human expert evaluation study was performed, reaching a weighted Mean Absolute Error (MAE) of 0.11 for the Lower Resolution Diffusion Models and a weighted MAE of 0.22 for the URCDM.

PaperPDFCode

Code

lucidrains/imagen-pytorch officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Generationwhole slide images

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionMAE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections