论文标题
消失点引导自然图像缝制
Vanishing Point Guided Natural Image Stitching
论文作者
论文摘要
最近，改善缝合图像的自然性的工作吸引了越来越广泛的关注。以前的方法遭受了严重的投影扭曲和不自然旋转的故障，尤其是当相关图像数量较大或图像涵盖非常广泛的视野时。在本文中，我们提出了一种新颖的自然图像缝合方法，该方法考虑了消失点以应对上述故障的指导。受到重要观察的启发，即曼哈顿世界中相互正交的消失点可以提供真正有用的方向线索，我们设计了一个方案，以有效地估算图像相似性的事先估算。鉴于像全球相似性约束一样估计的先前，我们将其归为流行的网格变形框架，以实现令人印象深刻的自然缝线性能。与其他现有方法（包括APAP，SPHP，AANAP和GSP）相比，我们的方法在自然图像缝线上进行了定量和定性实验中的最新性能。
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.
