提出可微渲染的不确定性下界，实现多智能体位姿估计的严格量化。
Multi-Agent Pose Uncertainty: A Differentiable Rendering Cramér-Rao Bound
- 用可微渲染建模观测，推导位姿估计的紧致不确定性下界。
- 在多相机系统中融合费舍尔信息，实现跨视角不确定性传播。
- 无需关键点匹配，适用于协同感知与新视角合成任务。
位姿估计在计算机视觉与机器人领域至关重要。尽管应用广泛，现有方法对密集或学习型模型下的位姿不确定性仍缺乏严格量化。本文将可微渲染视为测量函数，推导出相机位姿估计协方差的闭式下界。通过在流形上对小位姿扰动线性化图像形成过程，获得具渲染感知的Cramér-Rao下界。该方法退化为经典捆绑调整的不确定性，确保与视觉理论的一致性，并可通过融合各相机的费舍尔信息自然拓展至多智能体场景。该统计框架在无需显式关键点对应的情况下，可用于协同感知与新视角合成等下游任务。
原文摘要 · Abstract (English)
Pose estimation is essential for many applications within computer vision and robotics. Despite its uses, few works provide rigorous uncertainty quantification for poses under dense or learned models. We derive a closed-form lower bound on the covariance of camera pose estimates by treating a differentiable renderer as a measurement function. Linearizing image formation with respect to a small pose perturbation on the manifold yields a render-aware Cramér-Rao bound. Our approach reduces to classical bundle-adjustment uncertainty, ensuring continuity with vision theory. It also naturally extends to multi-agent settings by fusing Fisher information across cameras. Our statistical formulation has downstream applications for tasks such as cooperative perception and novel view synthesis without requiring explicit keypoint correspondences.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。