Light-field depth estimation powers salient object detection

Compared to traditional RGB images, light field images fulfill the demand for high-dimensional information in salient object detection. In this paper, we propose a salient object detection method based on light field depth estimation. In particular, we adopted a supervised learning approach for the design of the light field depth estimation algorithm. Subaperture images in each of the 4 viewing directions are constructed into epipolar plane images (EPI) as inputs to the multistream network. The multi-stream network consists of 4 branches, each containing a specific number of convolutional modules to extract the depth information in the epipolar plane images of the corresponding directions. The features extracted from the 4 branches are fed into the merged network to compute the correlation between the different epipolar plane images. The obtained disparity maps and RGB images are simultaneously inputted into a two-stream convolutional neural network for training. The trained model can achieve highly generalized and robust light field salient object detection. Experiments with real-world light field images indicate the superior performance of our method for clearly plotting the boundaries of saliency objects.