Vanishing Point Guided Natural Image Stitching

TL;DR

This paper introduces a vanishing point guided image stitching method that leverages Manhattan world assumptions to improve naturalness and reduce distortions in wide-field, multi-image stitching scenarios.

Contribution

It proposes a novel approach using vanishing points to estimate image similarity priors, enhancing naturalness in stitched images within a mesh deformation framework.

Findings

Achieves state-of-the-art results in natural image stitching

Reduces projective distortion and unnatural rotations

Outperforms existing methods like APAP, SPHP, AANAP, and GSP

Abstract

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.