手术视频生成综述：从扩散模型到世界模型
原标题：Surgical Video Generation From Diffusion to World Models: A Survey
AI 摘要
这篇综述论文系统梳理了2024至2026年间手术视频生成领域的研究进展，将其分为无条件生成、条件生成和世界模型生成三类范式，揭示了从合成视觉上合理的帧到建模手术场景因果动态的任务定义转变。论文指出像素级保真度与临床合理性之间存在持续差距，并将泛化能力、物理真实性、可控性和可解释性视为主要瓶颈。该综述为智能感知、多模态融合、生成式AI和手术数据科学交叉领域的研究者提供了结构化参考。
正文节选
Surgical Video Generation From Diffusion to World Models: A Survey Thanks: This work was partially supported by National Natural Science Fund of China under Grants 92570110 and 62271090, Chongqing Natural Science Fund under Grant CSTB2024NSCQ-JQX0038, and National Youth Talent Project. Abstract Surgical video data provides the primary training resource for models of intraoperative perception, surgical workflow understanding, and robotic decision-making. However, clinical data acquisition remains