SurgGraph: Quantitative Laparoscopic Video Understanding via Geometry-Grounded Scene Graphs
Surgical videos are a primary resource for teaching trainees anatomy, tool usage, and procedural skills. Yet learning from them at scale requires systems that understand surgical scenes. Existing approaches fall short: vision-language models lack fine-grained domain reasoning, task-specific models do not generalize, an...
Jing-Ying Wang, Rosiana Natalie, Marquise D. Singleterry et al.
· 0 citations