An analysis-by-synthesis framework for face recognition with variant pose, illumination and expression (PIE) is proposed in this paper. First, an efficient 2D-to-3D integrated fac...
Yuxiao Hu, Dalong Jiang, Shuicheng Yan, Lei Zhang,...
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
In this paper we propose a new method for the simultaneous segmentation and 3D reconstruction of interest point based articulated motion. We decompose a set of point tracks into r...
A large number of the world's cultural heritage sites and landscapes have been lost over time due to the progress of urbanization. Digital archive projects that digitize these...
In this paper we focus on using local 3D structure for segmentation. A tensor descriptor is estimated for each neighbourhood, i.e. for each voxel in the data set. The tensors are ...
Carl-Fredrik Westin, Abhir Bhalerao, Ron Kikinis, ...