Image-Based Modeling by Joint Segmentation

@article{citeulike:1428201, abstract = {Abstract\ \ The paper first traces the image-based modeling back to feature tracking and factorization that have been developed in the group led by Kanade since the eighties. Both feature tracking and factorization have inspired and motivated many important algorithms in structure from motion, 3D reconstruction and modeling. We then revisit the recent quasi-dense approach to structure from motion. The key advantage of the quasi-dense approach is that it not only delivers the structure from motion in a robust manner for practical modeling purposes, but also it provides a cloud of sufficiently dense 3D points that allows the objects to be explicitly modeled. To structure the available 3D points and registered 2D image information, we argue that a joint segmentation of both 3D and 2D is the fundamental stage for the subsequent modeling. We finally propose a probabilistic framework for the joint segmentation. The optimal solution to such a joint segmentation is still generally intractable, but approximate solutions are developed in this paper. These methods are implemented and validated on real data set.}, author = {Quan, Long and Wang, Jingdong and Tan, Ping and Yuan, Lu }, citeulike-article-id = {1428201}, doi = {10.1007/s11263-007-0044-1}, journal = {International Journal of Computer Vision}, keywords = {features, segmentation, stereo}, posted-at = {2007-07-02 09:09:03}, priority = {2}, title = {Image-Based Modeling by Joint Segmentation}, url = {http://dx.doi.org/10.1007/s11263-007-0044-1} }

TY - JOUR ID - citeulike:1428201 L3 - citeulike-article-id:1428201 TI - Image-Based Modeling by Joint Segmentation JF - International Journal of Computer Vision N2 - Abstract  The paper first traces the image-based modeling back to feature tracking and factorization that have been developed in the group led by Kanade since the eighties. Both feature tracking and factorization have inspired and motivated many important algorithms in structure from motion, 3D reconstruction and modeling. We then revisit the recent quasi-dense approach to structure from motion. The key advantage of the quasi-dense approach is that it not only delivers the structure from motion in a robust manner for practical modeling purposes, but also it provides a cloud of sufficiently dense 3D points that allows the objects to be explicitly modeled. To structure the available 3D points and registered 2D image information, we argue that a joint segmentation of both 3D and 2D is the fundamental stage for the subsequent modeling. We finally propose a probabilistic framework for the joint segmentation. The optimal solution to such a joint segmentation is still generally intractable, but approximate solutions are developed in this paper. These methods are implemented and validated on real data set. KW - features KW - segmentation KW - stereo AU - Quan, Long AU - Wang, Jingdong AU - Tan, Ping AU - Yuan, Lu UR - http://dx.doi.org/10.1007/s11263-007-0044-1 ER -