Uncalibrated View Synthesis Using Planar Segmentation of Images

This paper presents an uncalibrated view synthesis method using piecewise planar regions that are extracted from a given set of image pairs through planar segmentation. Our work concentrates on a view synthesis method that does not need estimation of camera parameters and scene structure. For our goal, we simply assume that images of real world are composed of piecewise planar regions. Then, we perform view synthesis simply with planar regions and homographies between them. Here, for accurate extraction of planar homographies and piecewise planar regions in images, the proposed method employs iterative homography estimation and color segmentation-based planar region extraction. The proposed method synthesizes the virtual view image using a set of planar regions as well as a set of corresponding homographies. Experimental comparisons with the images synthesized using the actual three-dimensional (3-D) scene structure and camera poses show that the proposed method effectively describes scene changes by viewpoint movements without estimation of 3-D and camera information.