Two-Stream Refinement Network for RGB-D Saliency Detection
Di Liu, Yaosi Hu, Kao Zhang, Zhenzhong Chen · 2019
In this paper, we propose a two-stream refinement network for RGB-D saliency detection. A fusion refinement module is designed to fuse output features from different resolution and modals. The structure information from depth helps distinguish between foreground and background and the lower level features with higher resolution can be adopted to refine the boundary of detected targets. The proposed model predicts high-resolution saliency map and then use a propagation-based module to further refine object boundary. Experimental results demonstrate that the proposed method performs well against to the state of the art methods on the recent RGB-D salient object detection dataset.