Spatial transcriptomics provides an unprecedented perspective for deciphering tissue spatial heterogeneity. However, high-resolution spatial transcriptomic technology remains constrained by limited gene coverage, technical complexity, and high cost. Existing spatial transcriptomics super-resolution methods from low resolution data suffer from two fundamental limitations: poor out-of-distribution generalization stemming from a neglect of inherent biological heterogeneity, and a lack of physical consistency. To address these challenges, we propose SRast, a novel physically constrained generalist framework designed for robust spatial transcriptomics super-resolution. To tackle heterogeneity, SRast employs a strategic decoupling architecture that explicitly decouples gene semantics representation from spatial geometry deconvolution, utilizing self-supervised learning to align latent distributions and mitigate cross-sample shifts. Regarding physical priors, SRast reformulates the task as ratio prediction on the simplex, performing a flow matching model to learn optimal transport-based geometric transformations that strictly enforce local mass conservation. Extensive experiments across diverse species, tissues, and platforms demonstrate that SRast achieves state-of-the-art performance, exhibiting superior zero-shot generalization capabilities and ensuring physical consistency in recovering fine-grained biological structures.
@article{arxiv.2602.10644,
title = {Towards Universal Spatial Transcriptomics Super-Resolution: A Generalist Physically Consistent Flow Matching Framework},
author = {Xinlei Huang and Weihao Dai and Zijun Qin and Xin Yu and Di Wang and Yanran Liu and Lixin Cheng and Xubin Zheng},
journal= {arXiv preprint arXiv:2602.10644},
year = {2026}
}