SuPerPM: A Large Deformation-Robust Surgical Perception Framework Based on Deep Point Matching Learned from Physical Constrained Simulation Data

arXiv:2309.13863v2 Announce Type: replace
Abstract: Manipulation of tissue with surgical tools often results in large deformations that current methods in tracking and reconstructing algorithms have not effectively addressed. A major source of tracking errors during large deformations stems from wrong data association between observed sensor measurements with previously tracked scene. To mitigate this issue, we present a surgical perception framework, SuPerPM, that leverages learning-based non-rigid point cloud matching for data association, thus accommodating larger deformations. The learning models typically require …

abstract algorithms arxiv association cs.cv current data errors framework major manipulation perception results robust simulation tools tracking type