Feature matching is a crucial task in the field of computer vision, which
involves finding correspondences between images. Previous studies achieve
remarkable performance using learning-based feature comparison. However, the
pervasive presence of matching redundancy between images gives rise to
unnecessary and error-prone computations in these methods, imposing limitations
on their accuracy. To address this issue, we propose MESA, a novel approach to
establish precise area (or region) matches for efficient matching redundancy
reduction. MESA first leverages the advanced image understanding capability of
SAM, a state-of-the-art foundation model for image segmentation, to obtain
image areas with implicit semantic. Then, a multi-relational graph is proposed
to model the spatial structure of these areas and construct their scale
hierarchy. Based on graphical models derived from the graph, the area matching
is reformulated as an energy minimization task and effectively resolved.
Extensive experiments demonstrate that MESA yields substantial precision
improvement for multiple point matchers in indoor and outdoor downstream tasks,
e.g. +13.61% for DKM in indoor pose estimation.

在计算机视觉领域中，特征匹配是一项至关重要的任务，先前的研究在使用基于学习的特征对比时取得了显著的性能。然而，图像之间存在的匹配冗余普遍导致这些方法中的不必要和容易出错的计算，限制了其准确性。为了解决这个问题，我们提出了 MESA，一种用于减少匹配冗余的建立精确区域匹配的新方法。MESA 首先利用 SAM 的先进图像分割模型的图像理解能力，获得具有隐含语义的图像区域。然后，提出了一个多关系图来建模这些区域的空间结构并构建它们的尺度层次结构。基于从图中得出的图形模型，将区域匹配重新定义为能量最小化任务并有效解决。大量实验证明，在室内和室外下游任务中，如室内位姿估计中的 DKM，MESA 为多点匹配器提供了显著的精度改进，例如室内位姿估计中的 + 13.61%。