Geometric context from a single image
Top Cited Papers
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15505499) , 654-661 Vol. 1
- https://doi.org/10.1109/iccv.2005.107
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.Keywords
This publication has 18 references indexed in Scilit:
- Automatic photo pop-upPublished by Association for Computing Machinery (ACM) ,2005
- On Symmetry and Multiple-View Geometry: Structure, Pose, and Calibration from a Single ImageInternational Journal of Computer Vision, 2004
- Is bottom-up attention useful for object recognition?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Learning a restricted bayesian network for object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Probabilistic spatial context models for scene content understandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Learning a classification model for segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Contextual Priming for Object DetectionInternational Journal of Computer Vision, 2003
- Self-calibration and metric reconstruction in spite of varying and unknown internal camera parametersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Statistical cues for domain specific image segmentation with performance analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Creating Architectural Models from ImagesComputer Graphics Forum, 1999