Sorry, you need to enable JavaScript to visit this website.

Additional depth information from RGBD images is one of characteristics different from conventional 2D images. Saliency detection aims to detect the attractive objects to human viewers in an image. Generally, saliency cues from different features are measured and fused into a single saliency using a linear or experiential fusion formula. we introduce a multi-stage depth-aware saliency model to fuse multiple saliency maps in a discriminative method.