发表机构
School of Automation, Southeast University; School of Computer Science and Technology, Tongji University; Institute of Artificial Intelligence, University of Science and Technology Beijing; School of Robotics, Wuhan University; Graduate School of Information, Production and Systems, Waseda University（东南大学自动化学院; 同济大学计算机科学与技术学院; 北京科技大学人工智能研究院; 武汉大学机器人学院; 早稻田大学信息生产系统研究科）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述梳理跨视图特征匹配领域进展，构建结构化分类体系，开展统一基准测试，提炼设计原则，探讨开放挑战，为该领域发展提供全面参考。
AI 中文摘要
跨视图特征匹配旨在在视角差异极大的图像间建立可靠的对应关系。过去十年，该领域已从特定任务模型发展为日益统一、可泛化的对应模型，近期视觉基础模型（Vision Foundation Models, VFMs）的出现进一步推动了研究进展。尽管取得了这些进展，但现有研究在问题表述、模型架构、训练范式和评估协议方面仍存在高度多样性，导致难以对该领域形成统一理解。本综述对跨视图特征匹配进行了系统性梳理：首先介绍涵盖特征提取、单类型特征匹配器、多类型特征匹配器、基于VFMs的方法、训练策略与鲁棒估计的结构化分类体系，为分析与比较提供连贯框架；进一步考察近期进展，提炼关键设计原则，强调向统一、可泛化对应模型的转变；还在统一协议下对代表性最先进方法开展了系统性实验基准测试，实现公平且全面的性能对比；此外，探讨了效率、极端条件下鲁棒性、跨域泛化等开放挑战与未来方向。本综述旨在为理解视觉基础模型时代跨视图特征匹配的演变、当前态势及未来发展提供全面且结构化的参考。
英文摘要
Cross-view feature matching aims to establish reliable correspondences across images with large viewpoint variations. Over the past decade, the field has evolved from task-specific models toward increasingly unified and generalizable correspondence models, with recent progress further driven by the emergence of vision foundation models (VFMs). Despite these advances, existing studies remain highly diverse in their problem formulations, model architectures, training paradigms, and evaluation protocols, making it difficult to obtain a unified understanding of the field. In this survey, we present a unified review of cross-view feature matching. We first introduce a structured taxonomy covering feature extraction, single-type feature matcher, multi-type feature matcher, VFMs based methods, training strategy and robust estimation, providing a coherent framework for analysis and comparison. We further examine recent advances, distilling key design principles and highlighting the shift toward unified and generalizable correspondence models. We also provide a unified experimental benchmarking of representative state-of-the-art methods under consistent protocols, enabling fair and comprehensive performance comparisons. In addition, we discuss open challenges and future directions, including efficiency, robustness under extreme conditions, and cross-domain generalization. This survey aims to provide a comprehensive and structured reference for understanding the evolution, current landscape, and future development of cross-view feature matching in the era of vision foundation models.
CommentsThis manuscript goes beyond a conventional survey. It proposes a new taxonomy for cross-view feature matching, provides extensive benchmarking under unified datasets and protocols, and offers original analysis from the perspective of vision foundation models. These contributions provide substantive methodological synthesis, empirical findings, and new research insights
