Title | ||
---|---|---|
A Variational Model for the Joint Recovery of the Fundamental Matrix and the Optical Flow |
Abstract | ||
---|---|---|
Traditional estimation methods for the fundamental matrix rely on a sparse set of point correspondences that have been established by matching salient image features between two images. Recovering the fundamental matrix from dense correspondences has not been extensively researched until now. In this paper we propose a new variational model that recovers the fundamental matrix from a pair of uncalibrated stereo images, and simultaneously estimates an optical flow field that is consistent with the corresponding epipolar geometry. The model extends the highly accurate optical flow technique of Brox et al.(2004) by taking the epipolar constraint into account. In experiments we demonstrate that our approach is able to produce excellent estimates for the fundamental matrix and that the optical flow computation is on par with the best techniques to date. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-69321-5_32 | DAGM-Symposium |
Keywords | Field | DocType |
optical flow field,corresponding epipolar geometry,new variational model,joint recovery,fundamental matrix,optical flow,epipolar constraint,accurate optical flow technique,best technique,optical flow computation,variational model,excellent estimate,dense correspondence,image features,epipolar geometry | Computer vision,Essential matrix,Eight-point algorithm,Epipolar geometry,Feature (computer vision),Variational model,Algorithm,Artificial intelligence,Optical flow,Fundamental matrix (computer vision),Mathematics,Salient | Conference |
Volume | ISSN | Citations |
5096 | 0302-9743 | 21 |
PageRank | References | Authors |
1.36 | 15 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Levi Valgaerts | 1 | 470 | 15.88 |
Andrés Bruhn | 2 | 1558 | 82.42 |
Joachim Weickert | 3 | 5489 | 391.03 |