Reproduce “Complexity-Aware Surgical Video Reasoning Segmentation with Digital Twin and Context Memory” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Yiqing Shen, Mathias Unberath

SurgReasonSeg maps implicit surgical requests to instrument masks by representing detected objects as labeled digital twins, routing queries to reasoning adapters, and using recent frames and retrieved cases. On temporal EndoVis-ReasonSeg queries, it reports J&F 0.654 versus 0.357 for ReSurgSAM2, with 18.8 FPS. Its candidate masks bound selection, and controls do not isolate individual modules.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.