학술논문
Geometric context from a single image
Document Type
Conference
Author
Source
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 Computer Vision Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on. 1:654-661 Vol. 1 2005
Subject
Language
ISSN
1550-5499
2380-7504
2380-7504
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 multiple-hypothesis framework for robustly estimating scene structure from a single image and obtaining confidences for each geometric label. These confidences can then be used to improve the performance of many other applications. We provide a thorough quantitative evaluation of our algorithm on a set of outdoor images and demonstrate its usefulness in two applications: object detection and automatic single-view reconstruction.