Abstract. This paper extends the recovery of structure and motion to image sequences with several independently moving objects. The motion, structure, and camera calibration are al...
: This paper proposes a manipulation technique to intuitively control multiple viewpoints of cameras in a 3D environment specifically, a primary viewpoint and additional viewpoints...
We present a fully-automated method for real-time and marker-free 3D human motion capture. The system computes the 3D shape of the person filmed from a synchronized camera set. We...
Structured-light methods actively generate geometric correspondence data between projectors and cameras in order to facilitate robust 3D reconstruction. In this paper, we present ...
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...