—In this paper, we present a novel method to reconstruct the large scale scenes from multiple calibrated images. It first generates a quasi-dense 3D point cloud of the scene by m...
Abstract. This paper presents an extended version of the fully automated 3D cerebral vessel reconstruction algorithm developed by Wilson and Noble [11] which is applicable to time-...
Recently, various technologies have become available for scanning real-world objects, enabling rapid and accurate shape acquisition. In most cases, such solutions have high cost, ...
To recognize three-dimensional objects it is important to
model how their appearances can change due to changes
in viewpoint. A key aspect of this involves understanding
which o...
Ronen Basri, Pedro F. Felzenszwalb, Ross B. Girshi...
This paper addresses the problem of recovering 3D non-rigid shape models from image sequences. For example, given a video recording of a talking person, we would like to estimate ...
Christoph Bregler, Aaron Hertzmann, Henning Bierma...