重新审视位姿先验与几何不确定性下的 3D 高斯泼溅位姿精化
Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty
把 3DGS 位姿精化中的位姿先验不确定性与重建几何不确定性显式建模，用蒙特卡洛位姿采样加 Fisher 信息加权 PnP 来稳定优化，可直接用于任何基于可微渲染的相机重定位流程，无需重训练。
原文依据 we introduce a relocalization framework that combines Monte Carlo pose sampling with Fisher Information-based PnP optimization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论3D 高斯泼溅（3DGS）近来已成为一种强大的场景表示，并越来越多地被用于视觉定位与位姿精化。然而，尽管其具备高质量的可微渲染能力，基于 3DGS 的位姿精化的鲁棒性仍对初始相机位姿与重建几何高度敏感。在本工作中，我们深入考察了这些局限，并识别出两类主要的不确定性来源：（i）位姿先验不确定性，通常源于回归或检索模型只输出单一确定性估计；（ii）几何不确定性，由 3DGS 重建的不完美所导致，其误差会传播进 PnP 求解器。这类不确定性会扭曲重投影几何并使优化不稳定，即使渲染外观看起来仍然合理。为应对这些不确定性，我们提出一个重定位框架，将蒙特卡洛位姿采样与基于 Fisher 信息的 PnP 优化相结合。我们的方法显式地同时考虑位姿不确定性与几何不确定性，且无需重新训练或额外监督。在多种室内与室外基准上，我们的方法一致地提升了定位精度，并在位姿噪声与深度噪声下显著增强了稳定性。
英文原文摘要 1296 字符
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.