Published several papers, such as 'Improving Generalization of Scene Coordinate Regression Through Query Pre-Training', 'Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration', 'Transitional Grid Maps: Efficient Analytical Inference of Dynamic Environments under Limited Sensing', etc.; Participated in multiple international conferences, such as ICCV, WACV, IROS, etc.
Research Experience
Computer Vision Researcher at Niantic Spatial; involved in multiple research projects including ACE-G, Neural Graph Map, Transitional Grid Maps, etc.
Education
Master's Degree, 2019; PhD Candidate, KTH
Background
A computer vision researcher working at Niantic Spatial and a PhD candidate at KTH. Main research interests lie at the intersection of 3D computer vision and robotics (and to a lesser degree, computer graphics). Particularly interested in the development of algorithms for robot perception such as pose and shape estimation of objects from partial information, dense SLAM, and visual relocalization.