发表机构
The Hong Kong University of Science and Technology (Guangzhou); The Hong Kong University of Science and Technology; Cheng Kar-Shun Robotics Institute（香港科技大学（广州）; 香港科技大学; 郑家纯机器人研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SFVO，一种基于预训练立体匹配与光流模型的对应驱动立体视觉里程计框架，通过解耦置信度图提升几何约束可靠性，实现鲁棒准确的位姿估计。
AI 中文摘要
基于深度学习的视觉里程计（VO）已取得显著进展，但现有大多数方法侧重于单目方法，其存在尺度模糊问题。立体视觉里程计天然提供真实度量，但在深度学习视觉里程计中研究较少，原因在于其高计算成本和建模复杂性。近期立体匹配和光流估计的进展使得密集视觉对应日益准确和可靠，但其互补的几何信息尚未被充分挖掘用于视觉里程计。本文提出SFVO，一种对应驱动的立体视觉里程计框架，直接构建于预训练的立体匹配和光流模型之上。SFVO利用预训练的立体匹配和光流模型来估计立体和时间对应关系。SFVO不直接从图像学习位姿，而是将学习到的对应关系映射为几何约束，并预测哪些点是可信的。为提高基于视觉对应的几何约束的可靠性，我们引入了针对旋转和平移的解耦置信度图。该设计更好地对齐了视觉对应与6自由度变换的特性。在室外和室内数据集上的大量实验表明，SFVO实现了鲁棒且准确的位姿估计，并具有强大的泛化能力。代码将公开。
英文摘要
Deep learning-based visual odometry (VO) has achieved significant progress, yet most existing methods focus on a monocular approach, which suffers from scale ambiguity. Stereo VO provides real metric by its nature, but remains less studied in deep learning VO due to its high computational cost and modeling complexity. Recent advances in stereo matching and optical flow estimation have made dense visual correspondence increasingly accurate and reliable, but their complementary geometric information has not been fully exploited for VO. In this paper, we present SFVO, a correspondence-driven stereo VO framework that directly builds upon pretrained stereo matching and optical flow models. SFVO exploits pretrained stereo matching and optical flow models to estimate stereo and temporal correspondences. Instead of learning pose directly from images, SFVO maps learned correspondences into geometric constraints and predicts which points are trustworthy. To improve the reliability of visual correspondence-based geometric constraints, we introduce decoupled confidence maps for rotation and translation. This design better aligns the characteristics of visual correspondence and 6-DoF transformations. Extensive experiments on outdoor and indoor datasets demonstrate that SFVO achieves robust and accurate pose estimation with strong generalization capability. The code will be released.
