Abstract: A method for creating a novel viewpoint image from a plurality of images includes the steps of simultaneously and continuously acquiring sets of images from a plurality of cameras. Predetermined background based correspondence fields are used to detect novel objects. Image representations are assigned for these objects likely new correspondences. These likely new correspondences are tested and further improved upon in a refinement step. The resulting correspondences are used to construct a novel viewpoint image.

Abstract: A method for creating visual telepresence for a large number of simultaneous users includes the step of simultaneously and continuously processing sets of images from a plurality of cameras to produce sets of short visual sequences that provide for virtual short movements in the environment. Additional steps include routing these many simultaneous repetitive short sequences to a plurality of user service processes. These short sequences are then composed into continuous video streams that provide convincing visual display of telepresence to many simultaneous users.

Abstract: A method for creating a novel viewpoint image from a plurality of images includes the steps of simultaneously and continuously acquiring sets of images from a plurality of cameras. Predetermined background based correspondence fields are used to detect novel objects. Image representations are assigned for these objects likely new correspondences. These likely new correspondences are tested and further improved upon in a refinement step. The resulting correspondences are used to construct a novel viewpoint image.