# 基于3D Gaussian Splatting的统一6自由度相机位姿估计

> 原文链接：https://robotics.hellobike.com/papers/2026-08-11-2608-10938
> 频道：papers | 更新日期：2026-08-11 | 标签：arxiv, cs.RO
> 核心摘要：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。

# 基于3D Gaussian Splatting的统一6自由度相机位姿估计

::: v-pre
> 原文链接：[GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting](https://arxiv.org/abs/2608.10938)（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
:::

## 原始参考来源 (Sources)

- [arXiv 2608.10938：GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting](https://arxiv.org/abs/2608.10938)