3D Head Reconstruction Using Multi-camera Stream

Given information from many cameras, one can hope to get a complete 3D representation of an object. Pintavirooj and Sangworasil exploit this idea and present a system that records sequentially images from multiple view points to reconstruct a 3D shape of a static object of interest [1]. For instance, using a 60 angle of view on the image, they manage to get its accurate 3D reconstruction [1]. Unfortunately, when considering application such as video surveillance, it is not reasonable to expect that 60 cameras will give simultaneous images of a person of interest. However, we can expect that the person will move over time and show sequentially different poses of her/his head to at least one or a few cameras. This article proposes a technique for recovering an accurate 3D shape by combining views recorded at different times.