We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds i...
For most iris capturing scenarios, captured iris images
could easily blur when the user is out of the depth of field
(DOF) of the camera, or when he or she is moving. The
common...
Xinyu Huang (University of Kentucky), Liu Ren (Rob...
We introduce a theoretical framework and practical algorithms for replacing time-coded structured light patterns with viewpoint codes, in the form of additional camera locations. ...
Mark Young, Erik Beeson, James Davis, Szymon Rusin...
Computer vision has traditionally focused on extracting structure, such as depth, from images acquired using thin-lens or pinhole optics. The development of computational imaging i...
1 We propose a novel video-based rendering algorithm with a single moving camera. We reconstruct a dynamic 3D model of the scene with a feature point set that "evolves" o...