Trendy suggestions for learning-based elastic warps enable the deep image stitchings to align images exposed to large parallax errors. Despite the remarkable alignments, the methods struggle with occasional holes or discontinuity between overlapping and non-overlapping regions of a target image as the applied training strategy mostly focuses on overlap region alignment. As a result, they require additional modules such as seam finder and image inpainting for hiding discontinuity and filling holes, respectively. In this work, we suggest Recurrent Elastic Warps (REwarp) that address the problem with Dirichlet boundary condition and boost performances by residual learning for recurrent misalign correction. Specifically, REwarp predicts a homography and a Thin-plate Spline (TPS) under the boundary constraint for discontinuity and hole-free image stitching. Our experiments show the favorable aligns and the competitive computational costs of REwarp compared to the existing stitching methods. Our source code is available at https://github.com/minshu-kim/REwarp.

翻译：针对基于学习的弹性扭曲方法的最新进展，使深度图像拼接能够对齐存在大视差误差的图像。尽管对齐效果显著，但由于训练策略主要关注重叠区域对齐，这些方法在目标图像的重叠与非重叠区域之间常出现偶然的孔洞或不连续性。为此，它们需要额外模块（如接缝查找器和图像修复）分别隐藏不连续性和填充孔洞。本文提出循环弹性扭曲（REwarp），通过狄利克雷边界条件解决该问题，并利用残差学习进行循环错位校正以提升性能。具体而言，REwarp在边界约束下预测单应性矩阵和薄板样条（TPS），实现无断裂、无孔洞的图像拼接。实验表明，与现有拼接方法相比，REwarp在保持良好对齐效果的同时具有竞争力的计算成本。我们的源代码发布于 https://github.com/minshu-kim/REwarp。