We propose a novel method for large-scale image stitching that is robust against repetitive patterns and featureless regions in the imagery. In such cases, state-of-the-art image stitching methods easily produce image alignment artifacts, since they may produce false pairwise image registrations that are in conflict within the global connectivity graph. Our method augments the current methods by collecting all the plausible pairwise image registration candidates, among which globally consistent candidates are chosen. This enables the stitching process to determine the correct pairwise registrations by utilizing all the available information from the whole imagery, such as unambiguous registrations outside the repeating pattern and featureless regions. We formalize the method as a weighted multigraph whose nodes represent the individual image transformations from the composite image, and whose sets of multiple edges between two nodes represent all the plausible transformations between the pixel coordinates of the two images. The edge weights represent the plausibility of the transformations. The image transformations and the edge weights are solved from a non-linear minimization problem with linear constraints, for which a projection method is used. As an example, we apply the method in a large-scale scanning application where the transformations are primarily translations with only slight rotation and scaling component. Despite these simplifications, the state-of-the-art methods do not produce adequate results in such applications, since the image overlap is small, which can be featureless or repetitive, and misalignment artifacts and their concealment are unacceptable.

我们提出了一种新的大规模图像拼接方法，该方法对图像中的重复模式和无特征区域具有鲁棒性。在这种情况下，最先进的图像拼接方法很容易产生图像对齐伪影，因为它们可能会产生在全局连接图中冲突的错误的成对图像配准。我们的方法通过收集所有合理的成对图像配准候选者来增强当前方法，其中选择全局一致的候选者。这使得拼接过程能够通过利用来自整个图像的所有可用信息来确定正确的成对配准，例如重复图案和无特征区域之外的明确配准。我们将该方法形式化为加权多重图，其节点表示来自合成图像的单个图像变换，其两个节点之间的多条边集表示两个图像的像素坐标之间的所有可能的变换。边权重表示变换的合理性。图像变换和边缘权重是从具有线性约束的非线性最小化问题中解决的，为此使用了投影方法。例如，我们将该方法应用于大规模扫描应用程序，其中转换主要是平移，只有轻微的旋转和缩放组件。尽管进行了这些简化，但最先进的方法在此类应用中并没有产生足够的结果，因为图像重叠很小，