Geometric Context from a Single Image

@misc{citeulike:967239, abstract = {Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric properties of a scene by learning appearance-based models of geometric classes, even in cluttered natural scenes. Geometric classes describe the 3D orientation of an image region with respect to the camera. We provide a multiplehypothesis framework for robustly estimating scene structure from a single image and obtaining...}, author = {Alexei, Derek H. }, citeulike-article-id = {967239}, keywords = {context, strcuture}, posted-at = {2006-12-12 08:08:53}, priority = {2}, title = {Geometric Context from a Single Image}, url = {http://citeseer.ist.psu.edu/744291.html} }

TY - GEN ID - citeulike:967239 L3 - citeulike-article-id:967239 TI - Geometric Context from a Single Image N2 - Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric properties of a scene by learning appearance-based models of geometric classes, even in cluttered natural scenes. Geometric classes describe the 3D orientation of an image region with respect to the camera. We provide a multiplehypothesis framework for robustly estimating scene structure from a single image and obtaining... KW - context KW - strcuture AU - Alexei, Derek UR - http://citeseer.ist.psu.edu/744291.html ER -