Abstract
We propose an affine framework for perspective views, captured by a single extremely simple equation based on a viewer-centered invariant we call relative affine structure. Via a number of corollaries of our main results we show that our framework unifies previous work-including Euclidean, projective and affine-in a natural and simple way, and introduces new, extremely simple, algorithms for the tasks of reconstruction from multiple views, recognition by alignment, and certain image coding applications.
Original language | English |
---|---|
Pages (from-to) | 873-883 |
Number of pages | 11 |
Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Volume | 18 |
Issue number | 9 |
DOIs | |
State | Published - 1996 |
Externally published | Yes |
Bibliographical note
Funding Information:A. Shashua acknowledges support from McDonnell-Pew postdoctoral fellowship (during 1993/94 at MIT), and recently support from US-IS Binational Science Foundation 94-00120/1 and by the European ACTS project No. AC074 VANGUARD. N. Navab was supported by a Nichidai Foundation fellowship provided by Prof. Aaron Bobick at MIT Media Laboratory.
Keywords
- Algebraic and geometric invariants
- Alignment
- Projective reometry
- Reprojection
- Structure from motion
- Visual recognition