Quasi-homography warps in image stitching
This work addresses the challenge of creating natural-looking panoramas for image stitching applications, representing an incremental improvement over existing warps.
The paper tackles the problem of balancing perspective and projective distortions in image stitching by proposing a quasi-homography warp, which outperforms state-of-the-art methods like homography, AutoStitch, and SPHP in urban scenes and wins most users' favor in a user study.
The naturalness of warps is gaining extensive attentions in image stitching. Recent warps such as SPHP and AANAP, use global similarity warps to mitigate projective distortion (which enlarges regions), however, they necessarily bring in perspective distortion (which generates inconsistencies). In this paper, we propose a novel quasi-homography warp, which effectively balances the perspective distortion against the projective distortion in the non-overlapping region to create a more natural-looking panorama. Our approach formulates the warp as the solution of a bivariate system, where perspective distortion and projective distortion are characterized as slope preservation and scale linearization respectively. Because our proposed warp only relies on a global homography, thus it is totally parameter-free. A comprehensive experiment shows that a quasi-homography warp outperforms some state-of-the-art warps in urban scenes, including homography, AutoStitch and SPHP. A user study demonstrates that it wins most users' favor, comparing to homography and SPHP.