GESTALT: Fast, Generalizable Histopathology Image Synthesis from Gene Expression with Pretrained Pathology Foundation Models
cs.CV
Submitted: 2026-10-31
Updated: 2026-10-31
Comments: Accepted at WACV 2027. 10 pages (8 main paper + 2 references), 4 figures. 8 pages of supplementary material
Code: https://github.com/trongnhandev1011/Gestalt
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- CytoSyn: a Foundation Diffusion Model for Histopathology -- Tech Report
- A Multimodal Foundation Model of Spatial Transcriptomics and Histology for Biological Discovery and Clinical Prediction
- A Generative Foundation Model for Multimodal Histopathology
- PixCell: A generative foundation model for digital histopathology images
- Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs