Abstract

Although depth information plays an important role in the human vision system, it is not yet well-explored in existing visual saliency computational models. In this work, we first introduce a large scale RGBD image dataset to address the problem of data deficiency in cur- rent research of RGBD salient ob ject detection. To make sure that most existing RGB saliency models can still be adequate in RGBD scenarios, we continue to provide a simple fusion framework that combines exist- ing RGB-produced saliency with new depth-induced saliency, the former one is estimated from existing RGB models while the latter one is based on the proposed multi-contextual contrast model. Moreover, a special- ized multi-stage RGBD model is also proposed which takes account of both depth and appearance cues derived from low-level feature contrast, mid-level region grouping and high-level priors enhancement. Extensive experiments show the effectiveness and superiority of our model which can accurately locate the salient ob jects from RGBD images, and also assign consistent saliency values for the target ob jects.