We present a novel approach to the reconstruction of depth from light field data. Our method uses dictionary representations and group sparsity constraints to derive a convex formulation. Although our solution results in an increase of the problem dimensionality, we keep numerical complexity at bay by restricting the space of solutions and by exploiting an efficient Primal-Dual formulation. Comparisons with state of the art techniques, on both synthetic and real data, show promising performances.
Title
A Convex Solution to Disparity Estimation from Light Fields via the Primal-Dual Method
Published in
Energy Minimization Methods In Computer Vision And Pattern Recognition, Emmcvpr 2015
Pagination
14
Series
Lecture Notes in Computer Science, 8932
Pages
350-363
Conference
10th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), Hong Kong, PEOPLES R CHINA, JAN 13-16, 2015
Date
2015
Publisher
Berlin, Springer-Verlag
ISSN
0302-9743
ISBN
978-3-319-14612-6
978-3-319-14611-9
Record creation date
2015-09-28