Object Stereo- Joint Stereo Matching and Object Segmentation

This paper presents a method for joint stereo matching and object segmentation. In the authors' approach a 3D scene is represented as a collection of visually distinct and spatially coherent objects. Each object is characterized by three different aspects: a color model, a 3D plane that approximates the object's disparity distribution, and a novel 3D connectivity property. Inspired by Markov Random Field models of image segmentation, they employ object-level color models as a soft constraint, which can aid depth estimation in powerful ways. In particular, their method is able to recover the depth of regions that are fully occluded in one input view, which to their knowledge is new for stereo matching.