MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos

🤗 Upvotes: 24 | cs.CV, cs.AI

Authors:
Rongsheng Wang, Junying Chen, Ke Ji, Zhenyang Cai, Shunian Chen, Yunjin Yang, Benyou Wang

Title:
MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos

Arxiv:
http://arxiv.org/abs/2507.05675v1

Abstract:
Recent advances in video generation have shown remarkable progress in open-domain settings, yet medical video generation remains largely underexplored. Medical videos are critical for applications such as clinical training, education, and simulation, requiring not only high visual fidelity but also strict medical accuracy. However, current models often produce unrealistic or erroneous content when applied to medical prompts, largely due to the lack of large-scale, high-quality datasets tailored to the medical domain. To address this gap, we introduce MedVideoCap-55K, the first large-scale, diverse, and caption-rich dataset for medical video generation. It comprises over 55,000 curated clips spanning real-world medical scenarios, providing a strong foundation for training generalist medical video generation models. Built upon this dataset, we develop MedGen, which achieves leading performance among open-source models and rivals commercial systems across multiple benchmarks in both visual quality and medical accuracy. We hope our dataset and model can serve as a valuable resource and help catalyze further research in medical video generation. Our code and data is available at https://github.com/FreedomIntelligence/MedGen