Multi-Agent Pose Uncertainty: A Differentiable Rendering Cramér-Rao Bound
This provides a statistical formulation for uncertainty in pose estimation, benefiting applications like cooperative perception and novel view synthesis in computer vision and robotics, though it is incremental as it builds on classical bundle-adjustment theory.
The paper tackles the problem of rigorous uncertainty quantification in camera pose estimation by deriving a closed-form lower bound on covariance using a differentiable renderer as a measurement function, extending it to multi-agent settings by fusing Fisher information across cameras.
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.