This website provides a RGBD salient object detection benchmark and comparison of existing algorithms and our RGBD model. It contains:
        1. A large scale benchmark containing 1,000 natural RGBD images together with human-marked ground truth.
        2. Evaluation of existing state-of-the-art algorithms and the proposed multi-stage RGBD model.
        3. The code of our model and the download link of the baseline algorithms.

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 current research of RGBD salient object 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 existing 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 specialized 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 objects from RGBD images, and also assign consistent saliency values for the target objects.

Paper
Houwen Peng, Bing Li, Weihua Xiong, Weiming Hu and Rongrong Ji. RGBD salient object detection: a benchmark and algorithmsIn Proceedings of the 13th European Conference on Computer Vision (ECCV2014). [Paper] [Poster] 
BibTeX:
@inproceedings{PengECCV14,
  author     =   {Houwen Peng and  Bing Li and Weihua Xiong and Weiming Hu and Rongrong Ji},
  title          =   {RGBD salient object detection: a benchmark and algorithms},
  booktitle =   {European Conference on Computer Vision (ECCV)},
  year          =   {2014},
  pages       =  {92-109}
}