Abstract | ||
---|---|---|
Stitched images provide a wide field-of-view (FoV) but suffer from unpleasant irregular boundaries. To deal with this problem, existing image rectangling methods devote to searching an initial mesh and optimizing a target mesh to form the mesh deformation in two stages. Then rectangu-lar images can be generated by warping stitched images. However, these solutions only work for images with rich linear structures, leading to noticeable distortions for por-traits and landscapes with non-linear objects. In this paper, we address these issues by proposing the first deep learning solution to image rectangling. Con-cretely, we predefine a rigid target mesh and only estimate an initial mesh to form the mesh deformation, contributing to a compact one-stage solution. The initial mesh is predicted using a fully convolutional network with a resid-ual progressive regression strategy. To obtain results with high content fidelity, a comprehensive objective function is proposed to simultaneously encourage the boundary rect-angular, mesh shape-preserving, and content perceptually natural. Besides, we build the first image stitching rectan-gling dataset with a large diversity in irregular boundaries and scenes. Experiments demonstrate our superiority over traditional methods both quantitatively and qualitatively. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/CVPR52688.2022.00565 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
Low-level vision, Datasets and evaluation, Image and video synthesis and generation | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lang Nie | 1 | 2 | 2.40 |
Chun-Yu Lin | 2 | 379 | 74.29 |
Kang Liao | 3 | 5 | 3.53 |
Shuaicheng Liu | 4 | 363 | 28.26 |
Yao Zhao | 5 | 1926 | 219.11 |