Three-Stream Cross-Modal Feature Aggregation Network for Light Field Salient Object Detection

Light field saliency detection can leverage the rich visual features of light field(LF) to highlight the salient regions, but existing CNN-based saliency detection methods are specifically designed for RGB image, not for light field. To tackle this problem, a three-stream cross-modal feature aggregation network is proposed for 4D light field saliency detection. To fully utilize the rich visual features of light field, three sub-networks are set up to analyse focal stack, all-focus image, and depth map respectively. Then, feature aggregation modules are used to aggregate cross-level features in a top-down manner. Finally, a cross-modal feature fusion module is designed to fuse the aggregated features of various modalities from the three sub-networks, which can identify salient object quickly and precisely. Extensive experiments on three benchmark datasets show that the effectiveness and superiority of the proposed algorithm qualitatively and quantitatively on five evaluation metrics compared with state-of-the-art(SOTA) methods.