Images formed by a human face change with viewpoint. A new technique is described for synthesizing images of faces from new viewpoints, when only a single 2D image is available. A...
Abstract. Volumetric structures are frequently used as shape descriptors for 3D data. The capture of such data is being facilitated by developments in multi-view video and range sc...
Gabriel J. Brostow, Irfan A. Essa, Drew Steedly, V...
Abstract. We present a segmentation method for vessels using an implicit deformable model with a soft shape prior. Blood vessels are challenging structures to segment due to their ...
The problem we consider in this paper is to take a single two-dimensional image containing a human body, locate the joint positions, and use these to estimate the body configurati...
A novel technique for multi-scale smoothing of a free-form 3-D surface is presented. Diffusion of the surface is achieved through convolutions of local parametrisations of the su...