Abstract Previous 2D saliency detection methods extract salient cues from a single view and directly predict the expected results. Both traditional and deeplearning-based 2D methods do not consider geometric information of 3D scenes. Therefore the relationship between scene understanding and salient objects cannot be effectively established. This limits the performance of 2D saliency detection in challenging scenes. In this paper, we show for the fifirst time that saliency detection problem can be reformulated as two sub-problems: light fifield synthesis from a single view and light-fifield-driven saliency detection. We propose a high-quality light fifield synthesis network to produce reliable 4D light fifield information. Then we propose a novel light-fifielddriven saliency detection network with two purposes, that is, i) richer saliency features can be produced for effective saliency detection; ii) geometric information can be considered for integration of multi-view saliency maps in a view-wise attention fashion. The whole pipeline can be trained in an end-to-end fashion. For training our network, we introduce the largest light fifield dataset for saliency detection, containing 1580 light fifields that cover a wide variety of challenging scenes. With this new formulation, our method is able to achieve state-ofthe-art performance