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...
We propose a method of calibrating multiple camera systems that operates by adjusting the camera parameters and the 3D shape of objects onto silhouette observations. Our method em...
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...
In this paper we present a model-based algorithm for the estimation of 3D motion and the analysis of facial expressions of a speaking person. A set of facial animation parameters ...
The optimal spatial adaptation (OSA) method [1] proposed by Boulanger and Kervrann has proven to be quite effective for spatially adaptive image denoising. This method, in additio...