Tan, Ping

3D digital human reconstructions and avatars

3D visual-inertial odometry and autonomous mobile robot exploration with learned map prediction

A neural network for monocular point cloud estimation of human objects

Advanced subspace methods for low/mid-level vision

Generalized dynamic human digitalization with sparse-view cameras

Global Structure-from-Motion and Its Application

Image layer separation and application

Learn to predict geometry and semantics of human from a single image

Learning 3D scene synthesis from RGB-D Images

Learning camera localization via dense scene matching