选择与剪枝：一种用于两视图对应学习的可微因果序列化状态空间模型
Selecting and Pruning: A Differentiable Causal Sequentialized State-Space Model for Two-View Correspondence Learning
AI总结：
针对两视图对应学习现有方法的不足，提出基于Mamba的CorrMamba对应滤波器，结合因果序列化学习与局部上下文增强，在多项任务上取得SOTA性能，室外相对位姿估计AUC@20°提升2.58个百分点。
摘要：
两视图对应学习旨在通过识别图像对之间潜在的差异信息，辨别真实与错误对应关系。现有方法要么对信息同等处理，要么需要显式存储全部上下文，在实际场景中往往计算开销较大。受Mamba固有选择性的启发，我们提出**CorrMamba**——一种利用Mamba能力的对应关系滤波器，它能从真实对应中选择性挖掘信息，同时抑制错误对应带来的干扰，从而以更低成本实现自适应聚焦。为避免Mamba受无序关键点影响而削弱其空间信息挖掘能力，我们基于Gumbel-Softmax技术定制了一种因果序列化学习方法，以完全自主且可微的方式建立特征间的因果依赖关系。此外，我们设计了一个局部上下文增强模块，用于捕获对应剪枝所需的关键上下文线索，对核心框架形成补充。在相对位姿估计、视觉定位等任务上的大量实验及分析表明，CorrMamba取得了当前最优（SOTA）性能。值得注意的是，在室外相对位姿估计任务中，我们的方法在AUC@20°指标上比此前的SOTA高出2.58个绝对百分点，凸显了其实际应用优势。我们的代码将公开发布。
英文摘要：
Two-view correspondence learning aims to discern true and false correspondences between image pairs by recognizing their underlying different information. Previous methods either treat the information equally or require the explicit storage of the entire context, tending to be laborious in real-world scenarios. Inspired by Mamba's inherent selectivity, we propose \textbf{CorrMamba}, a \textbf{Corr}espondence filter leveraging \textbf{Mamba}'s ability to selectively mine information from true correspondences while mitigating interference from false ones, thus achieving adaptive focus at a lower cost. To prevent Mamba from being potentially impacted by unordered keypoints that obscured its ability to mine spatial information, we customize a causal sequential learning approach based on the Gumbel-Softmax technique to establish causal dependencies between features in a fully autonomous and differentiable manner. Additionally, a local-context enhancement module is designed to capture critical contextual cues essential for correspondence pruning, complementing the core framework. Extensive experiments on relative pose estimation, visual localization, and analysis demonstrate that CorrMamba achieves state-of-the-art performance. Notably, in outdoor relative pose estimation, our method surpasses the previous SOTA by $2.58$ absolute percentage points in AUC@20\textdegree, highlighting its practical superiority. Our code will be publicly available.
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。
