Depth Estimation From a Light Field Image Pair With a Generative Model

In this paper, we propose a novel method to estimate the disparity maps from a light field image pair captured by a pair of light field cameras. Our method integrates two types of critical depth cues, which are separately inferred from the epipolar plane images and binocular stereo vision into a global solution. At the same time, in order to produce highly accurate disparity maps, we adopt a generative model, which can estimate a light field image only with the central subaperture view and corresponding hypothesized disparity map. The objective function of our method is formulated to minimize two energy terms/differences. One is the difference between the two types of previously extracted disparity maps and the target disparity maps, directly optimized in the gray-scale disparity space. The other indicates the difference between the estimated light field images and the input light field images, optimized in the RGB color space. Comprehensive experiments conducted on real and virtual scene light field image pairs demonstrate the effectiveness of our method.