Non-rigid structure from motion (NRSFM) is a difficult, underconstrained problem in computer vision. The standard approach in NRSFM constrains 3D shape deformation using a linear...
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...
A uni ed framework for 3 D shape reconstruction allows us to combine image-based and geometry-based information sources. The image information is akin to stereo and shape-fromshad...
In this paper, we propose a novel method to simultaneously and accurately estimate the 3D shape and 3D motion of a dynamic scene from multiple-viewpoint calibrated videos. We follo...
We present a novel method to transfer speech animation recorded in low resolution videos onto realistic 3D facial models. Unsupervised learning is utilized on a speech video corpus...