Complete 3-D models from video: a global approach (WA-L3)

Author(s) : Bruno B. Gonçalves (ISR/IST, Portugal) Pedro M. Q. Aguiar (ISR/IST, Portugal)

Abstract : We address the automatic recovery of complete 3-D object models from video streams. Usually, complete 3-D models are built by fusing several depth maps, each computed from a small set of consecutive video frames, using structure from motion techniques. However, since from a small number of similar views, it is very difficult to obtain accurate depth maps, their fusion becomes nontrivial and human interaction is in general required to assemble the complete 3-D model. Instead of using intermediate depth maps, we propose a method to recover complete 3-D models {\it directly} from the 2-D motions in the {\it entire set} of available video frames. The difficulty that arises when processing long videos is that different regions of the object are seen at different time instants. Our method decides wether a region that has become visible is a region that was seen before, or a previously unseen region, by seeking the {\it simplest rigid object} that describes well the observed 2-D motions. This global approach increases significantly the accuracy of the estimates of the 3-D shape of the object and the 3-D motion of the camera. Experiments with artificial data and real video demonstrate the good performance of our method.

Menu