File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.cviu.2005.01.004
- Scopus: eid_2-s2.0-19744370144
- WOS: WOS:000229983400004
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Symmetry-based 3-D reconstruction from perspective images
Title | Symmetry-based 3-D reconstruction from perspective images |
---|---|
Authors | |
Keywords | 3-D reconstruction Homography group Structure from symmetry Symmetry group Symmetry-based matching |
Issue Date | 2005 |
Citation | Computer Vision and Image Understanding, 2005, v. 99, n. 2, p. 210-240 How to Cite? |
Abstract | Symmetry is an important geometric cue for 3-D reconstruction from perspective images. In this paper, we introduce a unified theoretical framework for extracting poses and structures of 2-D symmetric patterns in space from calibrated images. The framework uniformly encompasses all three fundamental types of symmetry, i.e., reflective, rotational, and translational, based on a systematic study of the homography groups in image induced by the symmetry groups in space. We claim that if a planar object admits rich enough symmetry, no 3-D geometric information is lost through perspective imaging. Based on two fundamental principles that utilize common spatial relations among symmetric objects, we have developed a prototype system which can automatically extract and segment multiple 2-D symmetric patterns present in a single perspective image. The result of such a segmentation is a hierarchy of new geometric primitives, called symmetry cells and complexes, whose 3-D structures and poses are fully recovered. Finally, we propose a new symmetry-based matching technique, which can effectively establish correspondences among the extracted symmetry cells across multiple images. We demonstrate the application of the proposed algorithms on image segmentation, matching, and 3-D reconstruction with extensive experimental results. The algorithms and systems are more accurate and easier to implement than existing point- or line-based methods. Published by Elsevier Inc. |
Persistent Identifier | http://hdl.handle.net/10722/326690 |
ISSN | 2023 Impact Factor: 4.3 2023 SCImago Journal Rankings: 1.420 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, Allen Y. | - |
dc.contributor.author | Huang, Kun | - |
dc.contributor.author | Rao, Shankar | - |
dc.contributor.author | Hong, Wei | - |
dc.contributor.author | Ma, Yi | - |
dc.date.accessioned | 2023-03-31T05:25:49Z | - |
dc.date.available | 2023-03-31T05:25:49Z | - |
dc.date.issued | 2005 | - |
dc.identifier.citation | Computer Vision and Image Understanding, 2005, v. 99, n. 2, p. 210-240 | - |
dc.identifier.issn | 1077-3142 | - |
dc.identifier.uri | http://hdl.handle.net/10722/326690 | - |
dc.description.abstract | Symmetry is an important geometric cue for 3-D reconstruction from perspective images. In this paper, we introduce a unified theoretical framework for extracting poses and structures of 2-D symmetric patterns in space from calibrated images. The framework uniformly encompasses all three fundamental types of symmetry, i.e., reflective, rotational, and translational, based on a systematic study of the homography groups in image induced by the symmetry groups in space. We claim that if a planar object admits rich enough symmetry, no 3-D geometric information is lost through perspective imaging. Based on two fundamental principles that utilize common spatial relations among symmetric objects, we have developed a prototype system which can automatically extract and segment multiple 2-D symmetric patterns present in a single perspective image. The result of such a segmentation is a hierarchy of new geometric primitives, called symmetry cells and complexes, whose 3-D structures and poses are fully recovered. Finally, we propose a new symmetry-based matching technique, which can effectively establish correspondences among the extracted symmetry cells across multiple images. We demonstrate the application of the proposed algorithms on image segmentation, matching, and 3-D reconstruction with extensive experimental results. The algorithms and systems are more accurate and easier to implement than existing point- or line-based methods. Published by Elsevier Inc. | - |
dc.language | eng | - |
dc.relation.ispartof | Computer Vision and Image Understanding | - |
dc.subject | 3-D reconstruction | - |
dc.subject | Homography group | - |
dc.subject | Structure from symmetry | - |
dc.subject | Symmetry group | - |
dc.subject | Symmetry-based matching | - |
dc.title | Symmetry-based 3-D reconstruction from perspective images | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.cviu.2005.01.004 | - |
dc.identifier.scopus | eid_2-s2.0-19744370144 | - |
dc.identifier.volume | 99 | - |
dc.identifier.issue | 2 | - |
dc.identifier.spage | 210 | - |
dc.identifier.epage | 240 | - |
dc.identifier.isi | WOS:000229983400004 | - |