重新思考在姿态先验和几何不确定性下的3D高斯点散布姿态细化
Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty
AI总结：
本文针对3DGS姿态细化的鲁棒性问题，提出结合蒙特卡洛姿态采样与Fisher信息PnP优化的重定位框架，提升定位精度和稳定性。
摘要：
3D高斯点散布（3DGS）最近 emerged 作为一种强大的场景表示，并越来越多地用于视觉定位和姿态细化。然而，尽管其具有高质量的可微分渲染，基于3DGS的姿态细化的鲁棒性仍然对初始相机姿态和重建几何高度敏感。在本文中，我们深入研究这些限制，并识别出两个主要的不确定性来源：（i）姿态先验不确定性，通常源于回归或检索模型输出的单一确定性估计，以及（ii）几何不确定性，由3DGS重建中的不完美性引起，这些不完美性会传播到PnP求解器中。这些不确定性可能会扭曲重投影几何并破坏优化，即使渲染的外观仍然看起来合理。为了解决这些不确定性，我们引入了一个重定位框架，结合蒙特卡洛姿态采样与基于Fisher信息的PnP优化。我们的方法明确考虑了姿态和几何不确定性，并且不需要重新训练或额外的监督。在多样化的室内和室外基准上，我们的方法一致地提高了定位精度，并显著增加了在姿态和深度噪声下的稳定性。
英文摘要：
3D Gaussian Splatting (3DGS) has recently emerged as a powerful scene representation and is increasingly used for visual localization and pose refinement. However, despite its high-quality differentiable rendering, the robustness of 3DGS-based pose refinement remains highly sensitive to both the initial camera pose and the reconstructed geometry. In this work, we take a closer look at these limitations and identify two major sources of uncertainty: (i) pose prior uncertainty, which often arises from regression or retrieval models that output a single deterministic estimate, and (ii) geometric uncertainty, caused by imperfections in the 3DGS reconstruction that propagate errors into PnP solvers. Such uncertainties can distort reprojection geometry and destabilize optimization, even when the rendered appearance still looks plausible. To address these uncertainties, we introduce a relocalization framework that combines Monte Carlo pose sampling with Fisher Information-based PnP optimization. Our method explicitly accounts for both pose and geometric uncertainty and requires no retraining or additional supervision. Across diverse indoor and outdoor benchmarks, our approach consistently improves localization accuracy and significantly increases stability under pose and depth noise.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
