MomentBA：用于可微分束调整中各向异性对应不确定性的二阶空间矩
MomentBA: Second-order Spatial Moments for Anisotropic Correspondence Uncertainty in Differentiable Bundle Adjustment
- Wuhan University（武汉大学）
- Hubei Technology Innovation Center for Spatiotemporal Information and Positioning Navigation（湖北时空信息与定位导航技术创新中心）
- Hubei Luojia Laboratory（湖北珞珈实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
MomentBA通过二阶空间矩推导各向异性对应不确定性并集成到可微分束调整中，在EuRoC和TartanAir数据集上提升单目视觉里程计精度与轨迹稳健性。
AI中文摘要：
大多数现有的视觉里程计（VO）系统将特征对应视为确定性测量或分配均匀不确定性，忽略了不同观测固有的定位模糊性。然而，由于边缘、重复图案和运动模糊等图像结构，对应不确定性通常是各向异性的，这会显著影响几何优化。在这项工作中，我们提出了MomentBA，一种几何感知的束调整框架，从局部相似性响应的二阶空间矩中推导出各向异性对应不确定性。所提出的方法不引入额外的协方差预测网络，而是直接将匹配响应分布转换为可解释的协方差估计，并将其作为对应特定的信息矩阵纳入束调整中，用于不确定性感知的残差加权。此外，所提出的公式被集成到可微分优化框架中，建立了对应不确定性与几何估计之间的直接联系。在EuRoC MAV和TartanAir v1 Hard数据集上的实验表明，与现有的基于特征和基于学习的方法相比，MomentBA提高了单目视觉里程计的准确性。所提出的各向异性协方差模型比固定和同向性不确定性模型实现了更低的旋转误差和更稳健的轨迹估计，验证了几何诱导的不确定性建模在具有挑战性的视觉环境中的有效性。
英文摘要：
Most existing visual odometry (VO) systems treat feature correspondences as deterministic measurements or assign uniform uncertainty, ignoring the inherent localization ambiguity of different observations. However, correspondence uncertainty is often anisotropic due to image structures such as edges, repetitive patterns, and motion blur, which can significantly affect geometric optimization. In this work, we propose MomentBA, a geometry-aware bundle adjustment framework that derives anisotropic correspondence uncertainty from second-order spatial moments of local similarity responses. Instead of introducing additional covariance prediction networks, the proposed method directly converts matching response distributions into interpretable covariance estimates and incorporates them into bundle adjustment as correspondence-specific information matrices for uncertainty-aware residual weighting. Furthermore, the proposed formulation is integrated into a differentiable optimization framework, establishing a direct connection between correspondence uncertainty and geometric estimation. Experiments on the EuRoC MAV and TartanAir v1 Hard datasets demonstrate that MomentBA improves monocular visual odometry accuracy compared with existing feature-based and learning-based approaches. The proposed anisotropic covariance model achieves lower rotational errors and more robust trajectory estimation than fixed and isotropic uncertainty models, validating the effectiveness of geometry-induced uncertainty modeling for challenging visual environments.
