pose graph optimization

本文提出一种基于几何驱动的数据优化方法，通过主轴对齐解决物体姿态估计中的噪声敏感、对称性混淆问题，且无需修改现有网络架构。

This study addresses the limitation of existing 6D pose tracking methods that rely on costly initialization or real-time reconstruction, thereby struggling to meet the real-time demands of robotic manipulation and augmented reality. To this end, this work proposes a lightweight framework for long-term rigid object tracking. Departing from conventional point-based optimization paradigms, the proposed method constructs a compact pose graph modeled exclusively with relative pose constraints weighted by geometrically aligned uncertainties, effectively decoupling computational complexity from the number of correspondences. Evaluated across four real-world benchmarks, the approach achieves accuracy comparable to reconstruction-based trackers at minimal optimization cost, offering an efficient and robust solution for real-time applications.

This work addresses the challenges of convergence and communication efficiency in distributed pose graph optimization (PGO) for multi-robot systems by proposing a novel approach based on a second-order continuous dynamical system on Lie groups. By introducing a damped particle model, the equilibrium points of the system are aligned with the first-order critical points of PGO. A fully distributed optimization algorithm is then constructed using the damped Euler–Poincaré equations together with a semi-implicit geometric integrator. The method jointly models states and velocities to enable neighbor state prediction, significantly enhancing convergence under high-latency communication, and provides a unified generalization of existing algorithms such as Riemannian gradient descent and Gauss–Newton. Experimental results demonstrate that the proposed solver consistently outperforms state-of-the-art distributed baselines on standard PGO datasets under both synchronous and asynchronous settings.

This work addresses the challenge in factor graph–based state estimation where local optimization methods often converge to suboptimal solutions, while existing globally optimal approaches based on convex relaxation are hindered by modeling complexity and high computational cost. To overcome these limitations, the paper proposes an efficient method for globally optimal estimation that automatically constructs a semidefinite programming (SDP)–based convex relaxation within general factor graphs. The approach innovatively leverages the Bayes tree structure from the GTSAM framework together with chordal sparsity to decompose and solve the SDP problem efficiently. Experimental results on 3D pose-graph SLAM and 2D localization benchmarks demonstrate that the proposed method achieves global optimality while significantly outperforming conventional local solvers in both scalability and computational efficiency.

To address the unreliable pose graph construction and motion synchronization challenges in multi-view point cloud registration, this paper proposes an end-to-end absolute pose estimation paradigm. First, matching distance is introduced as a principled reliability metric for pose graph construction, replacing handcrafted loss functions with direct global pose regression. Second, the method jointly optimizes feature interaction and structural awareness by integrating local geometric distribution modeling with adaptive attention mechanisms. Fully data-driven, it eliminates iterative optimization and post-processing. Evaluated on diverse indoor and outdoor datasets, the approach achieves a 12.7% improvement in pose graph construction accuracy and reduces overall registration error by 21.3%, demonstrating significantly enhanced robustness and cross-scene generalization capability.

本文提出了一种名为CP-Cert的新方法，通过利用中心路径来有效解决在机器人学中由于松弛退化导致难以认证的问题，并应用于位姿注册和点云数据关联。

This work addresses the computationally demanding yet critical nonlinear least-squares problem in pose estimation for real-time computer vision. By introducing a suitable parametrization of rotations, the problem is reformulated as a system of polynomial equations. The authors propose a novel class of resultant solvers based on Sylvester matrices that enable efficient closed-form solutions. This approach substantially reduces computational complexity while preserving high numerical accuracy. Experimental results demonstrate that the method outperforms state-of-the-art techniques in terms of runtime on both 3D–3D and 3D–2D pose estimation tasks, offering a practical solution for time-sensitive applications.

This work addresses the challenge of achieving temporally consistent and robust 6D object pose estimation from monocular RGB images, a critical requirement for stable visual feedback control in robotics. The authors propose a factor graph–based online optimization framework that, for the first time, jointly models object motion dynamics and pose measurement uncertainty. By integrating outlier rejection with an online smoothing strategy, the method delivers temporally coherent and robust pose tracking. Evaluated on standard benchmarks, the approach significantly improves pose estimation accuracy and demonstrates enhanced system stability in vision-based force-controlled robotic manipulation tasks, thereby providing reliable state estimates for robot control.

本文提出一种基于学习的视图图聚合方法，通过图神经网络从噪声相对位姿估计全局一致的相机外参，用于三维重建。

该研究针对视觉导航中几何扰动导致的自主姿态估计问题，采用全局Lipschitz优化方法有效验证并提高了系统的鲁棒性。