We present a novel learning-based approach to synthesize new views of a light field image. In particular, given the four corner views of a light field, the presented method estimates any in-between view. We use three sequential convolutional neural networks for feature extraction, scene geometry estimation and view selection. Compared to state-of-the-art approaches, in order to handle occlusions we propose to estimate a different disparity map per view. Jointly with the view selection network, this strategy shows to be the most important to have proper reconstructions near object boundaries. Ablation studies and comparison against the state of the art on Lytro light fields show the superior performance of the proposed method. Furthermore, the method is adapted and tested on light fields with wide baselines acquired with a camera array and, in spite of having to deal with large occluded areas, the proposed approach yields very promising results.

我们提出了一种新颖的基于学习的方法来合成光场图像的新视图。特别地，给定光场的四个角视图，所提出的方法估计任何中间视图。我们使用三个顺序卷积神经网络进行特征提取，场景几何估计和视图选择。与最新技术相比，为了处理遮挡，我们建议为每个视图估计不同的视差图。结合视图选择网络，该策略显示出在对象边界附近进行适当重构最重要。消融研究以及与Lytro光场的现有技术比较表明，该方法具有优越的性能。此外，该方法适用于使用相机阵列采集的具有较宽基线的光场，并进行了测试，