Depth Estimation with Light Field and Photometric Stereo Data Using Energy Minimization

Through the fusion of light fields and photometric stereo, two state-of-the-art computational imaging approaches, we improve the 3D reconstruction of objects. Light field imaging techniques observe a scene from different angles, which results in a strong absolute depth estimation of the scene. Photo...

Full description

Saved in:
Bibliographic Details
Published inProgress in Pattern Recognition, Image Analysis, Computer Vision, and Applications Vol. 10125; pp. 175 - 183
Main Authors Antensteiner, Doris, Štolc, Svorad, Huber-Mörk, Reinhold
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2017
Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
3D vision
Energy minimization
Light fields
Photometric stereo
Online AccessGet full text

Cover

More Information
Summary:Through the fusion of light fields and photometric stereo, two state-of-the-art computational imaging approaches, we improve the 3D reconstruction of objects. Light field imaging techniques observe a scene from different angles, which results in a strong absolute depth estimation of the scene. Photometric stereo uses multiple illuminations to reconstruct the surface of objects, which allows estimating fine local details of objects, even when no surface structure is present. We combine both approaches within a minimization algorithm, which exhibits an accurate absolute depth with a high sensitivity to fine surface details.
ISBN:9783319522760
3319522760
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-52277-7_22