3D Passive shape recovery from texture and silhouette information

Recent efforts attempt to combine together informations of different passive methods. Critical issues in this research are the choice of data and how to combine such data in order to increase the overall information. The combination of stereo matching and silhouette information has recently received considerable attention both for obtaining high quality 3D models and for modelling 3D dynamic scenes, an application often referred to as 3D video. This work, building on recent results, reformulates 3D geometry recovery from stereo and silhouette informaton within a classical deformable model framework. Experimental verification shows that the theoretical advantages of the proposed solution improve its robustness and computational speed.