In this paper we propose a novel Conditional Random Field (CRF) formulation for the semantic scene labeling problem which is able to enforce temporal consistency between consecuti...
This paper presents new techniques for improving the structural quality of automatically acquired architectural 3D models. Common architectural features like parallelism and ortho...
Abstract. Foreground and background segmentation is a typical problem in computer vision and medical imaging. In this paper, we propose a new learning based approach for 3D segment...
—This paper presents an application of fuzzy logic theory to the reconstruction of solid models from engineering drawings. In engineering drawing, two-dimensional (2D) orthograph...
This paper presents a semi-automatic wireframe acquisition system. The system uses real-time (25Hz) tracking of a user specified 2D wireframe and intermittent camera pose paramete...