Previous pixel-level change detection methods either contain a background updating step that is costly for moving cameras (background subtraction) or can not locate object positio...
We develop an integrated, probabilistic model for the appearance and three-dimensional geometry of cluttered scenes. Object categories are modeled via distributions over the 3D lo...
Erik B. Sudderth, Antonio B. Torralba, William T. ...
This paper explores the direct motion estimation problem assuming that video-rate depth information is available, from either stereo cameras or other sensors. We use these depth m...
Michael Harville, Ali Rahimi, Trevor Darrell, Gail...
The detection and tracking of three-dimensional human body models has progressed rapidly but successful approaches typically rely on accurate foreground silhouettes obtained using...
We propose novel algorithms for the detection, segmentation, recognition, and pose estimation of threedimensional objects. Our approach initially infers geometric primitives to de...