Local feature matching aims at finding correspondences between a pair of images. Although current detector-free methods leverage Transformer architecture to obtain an impressive performance, few works consider maintaining local consistency. Meanwhile, most methods struggle with large scale variations. To deal with the above issues, we propose Adaptive Spot-Guided Transformer (ASTR) for local feature matching, which jointly models the local consistency and scale variations in a unified coarse-to-fine architecture. The proposed ASTR enjoys several merits. First, we design a spot-guided aggregation module to avoid interfering with irrelevant areas during feature aggregation. Second, we design an adaptive scaling module to adjust the size of grids according to the calculated depth information at fine stage. Extensive experimental results on five standard benchmarks demonstrate that our ASTR performs favorably against state-of-the-art methods. Our code will be released on https://astr2023.github.io.

翻译：局部特征匹配旨在寻找一对图像之间的对应关系。尽管当前的无检测器方法利用Transformer架构取得了令人印象深刻的性能，但很少有工作考虑维持局部一致性。同时，大多数方法在处理大尺度变化时存在困难。为解决上述问题，我们提出了自适应点引导Transformer（ASTR）用于局部特征匹配，该方法在统一的粗到细架构中共同建模局部一致性和尺度变化。所提出的ASTR具有若干优点。首先，我们设计了一个点引导聚合模块，以避免特征聚合时干扰无关区域。其次，我们设计了一个自适应缩放模块，用于在精细阶段根据计算得到的深度信息调整网格大小。在五个标准基准上的大量实验结果表明，我们的ASTR相比最先进方法具有优越性能。我们的代码将发布在https://astr2023.github.io。