Reproduce “EndoS3:Endoscopic Semantic Splatting SLAM” 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

Mona Sheikh Zeinoddin, Benjamin Wright, Zafer Tandogdu, Greg Shaw, Evangelos Mazomenos, Danail Stoyanov

EndoS³ presents a semantic SLAM system for endoscopic video that separates camera motion from tissue and instrument movement. It estimates motion with instance masks, tracks the camera from static regions, and gives instances separate deformation models. Across five CRCD++ sequences, it averages 3.03 mm ATE-RMSE, versus 3.67 mm for SNI-SLAM, with best ATE in three of five; comparisons use ground-truth masks.

Summary by alphaXiv.

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