We present GSplatLoc, a camera localization method that leverages the differentiable rendering capabilities of 3D Gaussian splatting for ultra-precise pose estimation. By formulating pose estimation as a gradient-based optimization problem that minimizes discrepancies between rendered depth maps from a pre-existing 3D Gaussian scene and observed depth images, GSplatLoc achieves translational errors within 0.01 cm and near-zero rotational errors on the Replica dataset - significantly outperforming existing methods. Evaluations on the Replica and TUM RGB-D datasets demonstrate the method's robustness in challenging indoor environments with complex camera motions. GSplatLoc sets a new benchmark for localization in dense mapping, with important implications for applications requiring accurate real-time localization, such as robotics and augmented reality.
我们提出了GSplatLoc，一种利用三维高斯散射（3D Gaussian Splatting）可微渲染能力的相机定位方法，实现了超高精度的位姿估计。通过将位姿估计表述为一个基于梯度优化的问题，GSplatLoc通过最小化预先构建的三维高斯场景渲染深度图与观测深度图之间的差异，达到了前所未有的定位精度。在Replica数据集上，GSplatLoc的平移误差低至0.01厘米，旋转误差接近零，显著优于现有方法。 在Replica和TUM RGB-D数据集上的评估表明，该方法在复杂相机运动的室内环境中表现出极高的鲁棒性。GSplatLoc为密集映射中的定位任务设立了新的基准，对需要高精度实时定位的应用（如机器人技术和增强现实）具有重要意义。