Stereo is a useful technique for obtaining depth information from images. However, it is required that the baseline length between two cameras should be large to increase depth pr...
This paper presents a complete solution to estimating a sceneās 3D geometry and appearance from multiple 2D images by using a statistical inverse ray tracing method. Instead of ...
Abstract. In this work, we introduce a robust energy model for multiview 3D reconstruction that fuses silhouette- and stereo-based image information. It allows to cope with signiļ¬...
Kalin Kolev, Maria Klodt, Thomas Brox, Selim Esedo...
In this paper we propose a method for gene ranking from microarray experiments using multiple discriminants. The novelty of our approach is that a gene's relative rank is det...
Alfred O. Hero, Sepidarseh Zareparsi, Anand Swaroo...
In this paper we present a framework for semantic scene parsing and object recognition based on dense depth maps. Five viewindependent 3D features that vary with object class are e...