外观
论文arXiv 2608.109382 个月前
基于3D Gaussian Splatting的统一6自由度相机位姿估计
原文链接：GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting（arXiv 2608.10938 · 发布日期：2026-08-11）
GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting
针对鲁棒泛化与高精度难兼顾，GS-CPE结合几何粗估计与3DGS扭曲细化，在室内外基准和自定义数据集验证。
核心要点
- 视觉定位中，从场景坐标回归到直接位姿回归，鲁棒泛化与高精度仍难同时实现。
- GS-CPE采用由粗到细框架，在3DGS场景表示上先进行检索引导的几何粗位姿估计。
- 随后通过可见性感知的掩码RGB扭曲目标、多尺度优化和自适应重渲染细化位姿。
- 在多个室内外基准和自定义数据集上达到SOTA，精度与泛化均持续更优。
验证范围与局限：验证范围为7Scenes、Cambridge Landmarks、FAST-LIVO2及一个自定义数据集。
英文摘要 (Abstract)
Despite substantial progress in visual localization, from scene coordinate regression to direct camera pose regression, achieving both robust generalization and high accuracy remain challenging. This study introduces GS-CPE (Gaussian Splatting based Camera Pose Estimation), a coarse-to-fine framework for 6-DoF camera pose estimation that unifies geometry-based coarse pose estimation with robust 3D Gaussian Splatting (3DGS) warping based pose refinement. GS-CPE first estimates a coarse pose via retrieval-guided geometric pose estimation on a 3DGS scene representation, then refines it by minimizing a visibility aware masked RGB warping objective in a multi-scale optimization framework, with adaptive re-rendering. Extensive experiments on indoor and outdoor benchmarks including 7Scenes, Cambridge Landmarks, FAST-LIVO2 datasets, and a custom dataset demonstrate state-of-the-art performance, consistently outperforming in both accuracy and generalization.
作者：Huaiyuan Weng, Chul Min Yeum, Su-Min Kang
来源
本页事实对应的公开页面，以原文为准。