This paper presents a novel representation for three-dimensional objects in terms of affine-invariant image patches and their spatial relationships. Multi-view constraints associated with groups of patches are combined with a normalized representation of their appearance to guide matching and reconstruction, allowing the acquisition of true three-dimensional affine and Euclidean models from multiple images and their recognition in a single photograph taken from an arbitrary viewpoint. The proposed approach does not require a separate segmentation stage and is applicable to cluttered scenes. Preliminary modeling and recognition results are presented.
|Original language||English (US)|
|Journal||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|State||Published - Sep 1 2003|
|Event||2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Madison, WI, United States|
Duration: Jun 18 2003 → Jun 20 2003
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition