Abstract

We present an automatic approach to segment an object in calibrated images acquired from multiple viewpoints. Our system starts with a new piece- wise planar layer-based stereo algorithm that estimates a dense depth map that consists of a set of 3D planar surfaces. The algorithm is formulated using an en- ergy minimization framework that combines stereo and appearance cues, where for each surface, an appearance model is learnt using an unsupervised approach. By treating the planar surfaces as structural elements of the scene and reasoning about their visibility in multiple views, we segment the object in each image in- dependently. Finally, these segmentations are refined by probabilistically fusing information across multiple views. We demonstrate that our approach can seg- ment challenging objects with complex shapes and topologies, which may have thin structures and non-Lambertian surfaces. It can also handle scenarios where the object and background color distributions overlap signi ficantly.