Abstract
Light field cameras capture information about the incoming light from multiple directions, going beyond classical capturing of light intensity performed by regular RGB cameras. This enables the computation of more accurate depth maps compared to stereo methods based on conventional cameras. However, the very small angular resolution of light field cameras limits their practical use in 3D applications. In this paper, we introduce for the first time in the literature the use of light field camera arrays, with the aim of improving the depth maps while providing a wide field of view. In this context, a novel algorithm for multi-stereo matching based on light field camera arrays is proposed. The disparity maps for the sub-aperture images are computed based on light field camera pairs using a novel multi-scale and multi-window stereo-matching algorithm. A global energy minimization based on belief propagation is proposed to regularize the results. The resulting depth maps are efficiently fused by means of k-means clustering. The proposed approach demonstrates very promising results for accurate 3D scene reconstruction and free navigation applications.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
