A novel deformable model for image segmentation and shape recovery is presented. The model is inspired by fluid dynamics and is based on a flooding simulation similar to the waters...
This paper presents a case-study of automatic construction of a hypertext from a large full-text document. The document we used as input of the automatic authoring process is a we...
Animating 3D faces to achieve compelling realism is a challenging task in the entertainment industry. Previously proposed face transfer approaches generally require a high-quality...
ROMA is a database of numerical images easily usable to evaluate in a systematic way the performance of road markings extraction algorithms. It comprises more than 100 original ima...
J.-P. Tarel, P. Nicolle, P. Charbonnier and T. Vei...
Remarkable performance has been reported to recognize single object classes. Scalability to large numbers of classes however remains an important challenge for today's recogn...
Marcus Rohrbach, Michael Stark, Gyö Szarvas, Bern...