用全局特征轨迹优化3D高斯点云，无需COLMAP也能精准重建。
TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints
- 通过特征轨迹建立全局几何约束，同步优化相机参数与3D高斯点云。
- 在真实与合成数据集上，姿态误差显著低于现有方法。
- 支持无COLMAP预处理，适合实际应用中的快速三维重建。
我们提出TrackGS，一种将全局特征轨迹融入3D高斯点云（3DGS）的新型方法，实现无需COLMAP的全新视图合成。尽管3DGS渲染质量出色，但其对精确预计算相机参数的依赖仍是主要瓶颈。现有免COLMAP方法依赖局部约束，在复杂场景中表现不佳。本工作核心创新在于利用特征轨迹建立全局几何约束，实现相机参数与3D高斯点云的联合优化。具体包括：(1) 引入轨迹约束的高斯点作为几何锚点；(2) 提出新颖的2D与3D轨迹损失函数以保证多视角一致性；(3) 推导相机内参优化的可微形式。在具有挑战性的真实世界与合成数据集上的大量实验表明，该方法达到当前最优性能，姿态误差显著降低，同时保持优异渲染质量。本方法无需COLMAP预处理，使3DGS更适用于实际应用场景。
原文摘要 · Abstract (English)
We present TrackGS, a novel method to integrate global feature tracks with 3D Gaussian Splatting (3DGS) for COLMAP-free novel view synthesis. While 3DGS delivers impressive rendering quality, its reliance on accurate precomputed camera parameters remains a significant limitation. Existing COLMAP-free approaches depend on local constraints that fail in complex scenarios. Our key innovation lies in leveraging feature tracks to establish global geometric constraints, enabling simultaneous optimization of camera parameters and 3D Gaussians. Specifically, we: (1) introduce track-constrained Gaussians that serve as geometric anchors, (2) propose novel 2D and 3D track losses to enforce multi-view consistency, and (3) derive differentiable formulations for camera intrinsics optimization. Extensive experiments on challenging real-world and synthetic datasets demonstrate state-of-the-art performance, with much lower pose error than previous methods while maintaining superior rendering quality. Our approach eliminates the need for COLMAP preprocessing, making 3DGS more accessible for practical applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。