Vanishing Point Guided Natural Image Stitching
This work addresses the problem of producing natural-looking stitched images for applications like photography and computer vision, representing an incremental improvement over prior techniques.
The paper tackles severe projective distortion and unnatural rotation in image stitching by introducing a method guided by vanishing points, achieving state-of-the-art performance in quantitative and qualitative experiments compared to existing methods.
Recently, works on improving the naturalness of stitching images gain more and more extensive attention. Previous methods suffer the failures of severe projective distortion and unnatural rotation, especially when the number of involved images is large or images cover a very wide field of view. In this paper, we propose a novel natural image stitching method, which takes into account the guidance of vanishing points to tackle the mentioned failures. Inspired by a vital observation that mutually orthogonal vanishing points in Manhattan world can provide really useful orientation clues, we design a scheme to effectively estimate prior of image similarity. Given such estimated prior as global similarity constraints, we feed it into a popular mesh deformation framework to achieve impressive natural stitching performances. Compared with other existing methods, including APAP, SPHP, AANAP, and GSP, our method achieves state-of-the-art performance in both quantitative and qualitative experiments on natural image stitching.