STREAM applies stochastic Riemannian flow matching on VFM-derived unit hypersphere latents with a novel anisotropic decoder to achieve SOTA reconstruction and generation on breast and colorectal cancer histopathology datasets.
arXiv:2506.05127 (2025)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
HistDiT introduces a structure-aware latent conditional DiT with dual-stream conditioning and multi-objective loss that outperforms GANs and U-Net diffusion models for high-fidelity virtual histological staining.
CHIS steers pretrained diffusion models to generate histopathology images aligned with input structural masks via frequency-domain structural initialization and wavelet-based textural modulation without any training on annotated data.
citing papers explorer
-
STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation
STREAM applies stochastic Riemannian flow matching on VFM-derived unit hypersphere latents with a novel anisotropic decoder to achieve SOTA reconstruction and generation on breast and colorectal cancer histopathology datasets.
-
Controllable Histopathology Image Synthesis with Training-free Structural Initialization and Textural Modulation
CHIS steers pretrained diffusion models to generate histopathology images aligned with input structural masks via frequency-domain structural initialization and wavelet-based textural modulation without any training on annotated data.