This paper describes methods for recovering time-varying shape and motion of nonrigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talkin...
Lorenzo Torresani, Aaron Hertzmann, Christoph Breg...
We present a novel ``dynamic learning'' approach for an intelligent image database system to automatically improve object segmentation and labeling without user interven...
We describe a hardware and software system for digitizing the shape and color of large fragile objects under non-laboratory conditions. Our system employs laser triangulation rang...
Marc Levoy, Kari Pulli, Brian Curless, Szymon Rusi...
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
Graph cut image segmentation with intensity information alone is prone to fail for objects with weak edges, in clutter, or under occlusion. Existing methods to incorporate shape a...