Rapid Light Field Depth Estimation with Semi-Global Matching

Abstract

Running time of the light field depth estimation algorithms is typically high. This assessment is based on the computational complexity of existing methods and the large amounts of data involved. The aim of our work is to develop a simple and fast algorithm for accurate depth computation. In this context, we propose an approach, which involves Semi-Global Matching for the processing of light field images. It forms on comparison of pixels' correspondences with different metrics in the substantially bounded light field space. We show that our method is suitable for the fast production of a proper result in a variety of light field configurations.

Nonlinear Optimization of Light Field Point Cloud

“…We provide a comparison of the proposed algorithm with the state-of-the-art methods, presented in Section 2 : BSL [ 18 ], FASTLFNET [ 20 ], EPI1 [ 16 ], EPI2 [ 12 ], EPINET [ 19 ], FSL [ 10 ], LF [ 40 ], LFOCC [ 15 ], OFSY [ 17 ], RM3DE [ 14 ], RPRF [ 41 ], SCGC [ 42 ], and SPO [ 43 ]. Qualitative comparison for one of the light field images from "training" category is presented in Figure 6 .…”

“…Strecke et al [ 17 ] estimate depth and normals using partial focal stacks with their joint optimization. Preceding methods [ 10 , 18 ] used a construction of matching cost volume in the bordered space with further cost refinement.…”

“…This section describes the steps for getting an initial disparity map, which is used afterwards as an initialization step for the further nonlinear optimization. For that, we follow and improve the disparity estimation algorithm, described in [ 10 ].…”

“…In this work, we present an extension of our depth estimation algorithm from [ 10 ]. An example of the result of our algorithm is demonstrated in Figure 1 .…”

Real-time per-pixel focusing method for light field rendering

“…Those with lowest disparity are chosen. In this way, disparity maps can be obtained from the light field images and filtered, resulting in an approximate depth map [11]. Optical flow based depth estimation methods using feature matching in images also exist but they are generally very slow [12].…”