VSFormer：用于对应关系剪枝的视觉-空间融合 Transformer
VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning
AI总结：
针对对应关系剪枝中缺乏视觉线索的问题，提出视觉-空间融合 Transformer（VSFormer），通过交叉注意力提取视觉线索并结合 KNN 图与 Transformer 捕获上下文，在室内外基准上优于现有方法。
摘要：
对应关系剪枝旨在从初始的假设对应集合中找到正确匹配（内点），这是许多应用的基础任务。由于显著的视觉差异导致场景/图像对之间的内点比率不断变化，这一寻找过程极具挑战性。然而，现有方法的性能通常受限于缺乏场景视觉线索（例如纹理、光照、结构）的问题。在本文中，我们提出了一种视觉-空间融合 Transformer（VSFormer）来识别内点并准确恢复相机位姿。首先，我们通过双视图图像局部特征之间的交叉注意力获取场景的高度抽象视觉线索。然后，我们通过一个联合视觉-空间融合模块对这些视觉线索和对应关系进行建模，同时将视觉线索嵌入到对应关系中以进行剪枝。此外，为了挖掘对应关系的一致性，我们还设计了一个结合基于 KNN 图和 Transformer 的新颖模块，有效捕获局部和全局上下文。大量实验表明，所提出的 VSFormer 在室外和室内基准上优于最先进的方法。我们的代码在以下仓库提供：https://github.com/sugar-fly/VSFormer。
英文摘要：
Correspondence pruning aims to find correct matches (inliers) from an initial set of putative correspondences, which is a fundamental task for many applications. The process of finding is challenging, given the varying inlier ratios between scenes/image pairs due to significant visual differences. However, the performance of the existing methods is usually limited by the problem of lacking visual cues (\eg texture, illumination, structure) of scenes. In this paper, we propose a Visual-Spatial Fusion Transformer (VSFormer) to identify inliers and recover camera poses accurately. Firstly, we obtain highly abstract visual cues of a scene with the cross attention between local features of two-view images. Then, we model these visual cues and correspondences by a joint visual-spatial fusion module, simultaneously embedding visual cues into correspondences for pruning. Additionally, to mine the consistency of correspondences, we also design a novel module that combines the KNN-based graph and the transformer, effectively capturing both local and global contexts. Extensive experiments have demonstrated that the proposed VSFormer outperforms state-of-the-art methods on outdoor and indoor benchmarks. Our code is provided at the following repository: https://github.com/sugar-fly/VSFormer.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
