StereoCut: Consistent interactive object selection in stereo image pairs

Methods of interacting with stereo image pairs are important for handling the increasing amount of stereoscopic 3D data now being produced. In this paper, we introduce a framework for interactively selecting objects in two stereo images simultaneously using graph cut. A key contribution of our method is the use of stereo correspondence probability distributions to govern the strength of the connection between the two images. This allows information from arbitrary stereo matching algorithms to be utilized by our method. We show how to enforce consistency in these distributions to improve the results. For comparisons, we introduce a new dataset of stereo images and ground truth selections. We evaluate different correspondence distributions and show that our method is effective in selecting objects from stereo pairs.