SEAGULL: Seam-guided Local Alignment for Parallax-tolerant Image Stitching

Kaimo Lin1,   Nianjuan Jiang2,   Loong-Fah Cheong1,   Minh Do2,   Jiangbo Lu2

1. National University of Singapore   2. Advanced Digital Sciences Center, Singapore


Image stitching with large parallax is a challenging problem. Global alignment usually introduces noticeable artifacts. A com- mon strategy is to perform partial alignment to facilitate the search for a good seam for stitching. Different from existing approaches where the seam estimation process is performed sequentially after alignment, we explicitly use the estimated seam to guide the process of optimizing lo- cal alignment so that the seam quality gets improved over each iteration. Furthermore, a novel structure-preserving warping method is introduced to preserve salient curve and line structures during the warping. These measures substantially improve the effectiveness of our method in dealing with a wide range of challenging images with large parallax.


Our Dataset

Zhang & Liu's Dataset [1]


[1] Zhang, F., Liu, F.: Parallax-tolerant image stitching. In: Proc. CVPR (2014)


        author = {Lin, Kaimo and Jiang, Nianjuan and Cheong, Loong-Fah and Do, Minh and Lu, Jiangbo},
        title = {SEAGULL: Seam-guided Local Alignment for Parallax-tolerant Image Stitching},
        booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})},
        year = {2016}