Depth cue enhancement and guidance network for RGB-D salient object detection

Xiang Li, Qing Zhang, Weiqi Yan, Meng Dai

Abstract: Highlights•We propose a depth cue enhancement and guidance network for RGB-D saliency detection.•A DCE module is designed to improve the quality of the depth map.•A UFE module is proposed to enhance the features’ discriminability and specificity.•We design a DFF module to effectively generate discriminative cross-modal features.•The proposed method performs competitively against the recent methods.