Previous 2D saliency detection methods extract salient cues from a single view and directly predict the expected results. Both traditional and deep-learning-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 first time that saliency detection problem can be reformulated as two sub-problems: light field synthesis from a single view and light-field-driven saliency detection. This paper first introduces a high-quality light field synthesis network to produce reliable 4D light field information. Then a novel light-field-driven saliency detection network is proposed, in which a Direction-specific Screening Unit (DSU) is tailored to exploit the spatial correlation among multiple viewpoints. The whole pipeline can be trained in an end-to-end fashion. Experimental results demonstrate that the proposed method outperforms the state-of-the-art 2D, 3D and 4D saliency detection methods. Our code is publicly available at https://github.com/OIPLab-DUT/ESCNet.

中文翻译：

---

探索光场显着性检测的空间相关性：从单一视图进行扩展


以前的 2D 显着性检测方法从单个视图中提取显着线索并直接预测预期结果。传统的和基于深度学习的 2D 方法都没有考虑 3D 场景的几何信息。因此无法有效地建立场景理解和显着对象之间的关系。这限制了具有挑战性的场景中 2D 显着性检测的性能。在本文中，我们首次证明显着性检测问题可以重新表述为两个子问题：单视图光场合成和光场驱动显着性检测。本文首先介绍了一种高质量的光场合成网络来产生可靠的 4D 光场信息。然后提出了一种新颖的光场驱动显着性检测网络，其中定制方向特定筛选单元（DSU）以利用多个视点之间的空间相关性。整个管道可以以端到端的方式进行训练。实验结果表明，所提出的方法优于最先进的 2D、3D 和 4D 显着性检测方法。我们的代码可在 https://github.com/OIPLab-DUT/ESCNet 上公开获取。