Reproduce “SCOPE-4D: Endoscopic 4D Geometry Foundation Models” 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
Chaoyi Zhou, Zhongpai Gao, Anwesa Choudhuri, Meng Zheng, Benjamin Planche, Run Wang, Terrence Chen, Siyu Huang and 1 more
SCOPE-4D jointly predicts camera motion, geometry, and tissue trajectories from monocular endoscopic video. It represents tissue movement as shared motion plus local deformation. On the seven-dataset in-domain average, geometry-only fine-tuning raises pose AUC@5° from 7.81 to 29.44 and lowers depth AbsRel from 0.093 to 0.042. On StereoMIS, EPE is 5.022 versus 6.266 for 4RC, but do not establish clinical readiness.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.