基于3D高斯溅射的相机位姿优化
Camera Pose Refinement via 3D Gaussian Splatting
AI总结：
针对现有相机位姿优化方法依赖特定描述符或网络、缺乏几何约束的局限，提出GS-SMC框架，利用3D高斯溅射模型，通过极几何约束迭代优化位姿，在两个数据集上误差显著降低，无需额外训练即可适配不同场景。
摘要：
相机位姿优化旨在提升3D计算机视觉应用中初始位姿估计的准确性。大多数优化方法依赖于特定描述符或专用网络的2D-3D对应关系，需要针对不同描述符重新重建场景，或针对每个场景完全重新训练网络。一些最新方法通过特征相似性推断位姿，但缺乏几何约束导致精度较低。为克服这些限制，我们提出一种利用3D高斯溅射（3DGS）的新型相机位姿优化框架，称为GS-SMC。鉴于3DGS的广泛应用，我们的方法可使用现有3DGS模型渲染新视图，提供轻量级解决方案，无需额外训练或微调即可直接应用于不同场景。具体而言，我们引入迭代优化方法，利用查询图像与多幅渲染图像之间的极几何约束优化相机位姿，且可灵活选择特征提取器和匹配器建立约束。在7-Scenes和Cambridge Landmarks数据集上的大量实证评估表明，该方法优于最先进的相机位姿优化方法，在7-Scenes上中位平移和旋转误差分别降低53.3%和56.9%，在Cambridge上分别降低40.7%和53.2%。
英文摘要：
Camera pose refinement aims at improving the accuracy of initial pose estimation for applications in 3D computer vision. Most refinement approaches rely on 2D-3D correspondences with specific descriptors or dedicated networks, requiring reconstructing the scene again for a different descriptor or fully retraining the network for each scene. Some recent methods instead infer pose from feature similarity, but their lack of geometry constraints results in less accuracy. To overcome these limitations, we propose a novel camera pose refinement framework leveraging 3D Gaussian Splatting (3DGS), referred to as GS-SMC. Given the widespread usage of 3DGS, our method can employ an existing 3DGS model to render novel views, providing a lightweight solution that can be directly applied to diverse scenes without additional training or fine-tuning. Specifically, we introduce an iterative optimization approach, which refines the camera pose using epipolar geometric constraints among the query and multiple rendered images. Our method allows flexibly choosing feature extractors and matchers to establish these constraints. Extensive empirical evaluations on the 7-Scenes and the Cambridge Landmarks datasets demonstrate that our method outperforms state-of-the-art camera pose refinement approaches, achieving 53.3% and 56.9% reductions in median translation and rotation errors on 7-Scenes, and 40.7% and 53.2% on Cambridge.
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。
