Geometric Structure Preserving Warp for Natural Image Stitching

Peng Du, Jifeng Ning, Jiguang Cui, Shaoli Huang, Xinchao Wang, Jiaxin Wang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 3688-3696

Abstract


Preserving geometric structures in the scene plays a vital role in image stitching. However, most of the existing methods ignore the large-scale layouts reflected by straight lines or curves, decreasing overall stitching quality. To address this issue, this work presents a structure-preserving stitching approach that produces images with natural visual effects and less distortion. Our method first employs deep learning-based edge detection to extract various types of large-scale edges. Then, the extracted edges are sampled to construct multiple groups of triangles to represent geometric structures. Meanwhile, a GEometric Structure preserving (GES) energy term is introduced to make these triangles undergo similarity transformation. Further, an optimized GES energy term is presented to reasonably determine the weights of the sampling points on the geometric structure, and the term is added into the Global Similarity Prior (GSP) stitching model called GES-GSP to achieve a smooth transition between local alignment and geometric structure preservation. The effectiveness of GES-GSP is validated through comprehensive experiments on a stitching dataset. The experimental results show that the proposed method outperforms several state-of-the-art methods in geometric structure preservation and obtains more natural stitching results. The code and dataset are available at https://github.com/flowerDuo/GES-GSP-Stitching.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Du_2022_CVPR, author = {Du, Peng and Ning, Jifeng and Cui, Jiguang and Huang, Shaoli and Wang, Xinchao and Wang, Jiaxin}, title = {Geometric Structure Preserving Warp for Natural Image Stitching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3688-3696} }