This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach...
We describe how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition. The model uses pro...
This paper presents a new framework for recovering superquadrics with global deformations from multi-view real range data. The framework aims at improving confidence and accuracy...
Yan Zhang, Joon Ki Paik, Andreas Koschan, Mongi A....
We propose a novel and robust model to represent and learn generic 3D object categories. We aim to solve the problem of true 3D object categorization for handling arbitrary rotati...
In GIS and spatial databases, cardinal directions are frequently used as selection and join criteria in query languages. However, most cardinal direction models are only able to h...