High resolution free-view interpolation of planar structure

In many applications, users desire to access a random viewing angle of a scene in high resolution while this specifically queried imagery is not among the acquired sample images. In theory, 3D reconstruction based rendering can generate such an image. However, accurate camera calibration over large scale photo collections is needed and is highly complex in nature. Image stitching based approachescan also be applied. However, such scheme is unable to provide free view interpolation or resolution enhancement. In this paper, we present a novel free view image super-resolution scheme to interpolate free views for planar structures. We construct a Bayesian model and marginalize it over photometric regulation and geometric registration parameters applying the Lie group theory. Experimental results show that the proposed scheme is able to achieve desired performance against the state-of-the-art image super-resolution approaches and successfully obtain registration in full 6 degree-of-freedom (DOF). Compared with existing image based rendering schemes, the proposed scheme achieves free view interpolation for planar structures with higher resolution and less distortion.