TrackGS: 通过全局轨迹约束优化无COLMAP的3D高斯点分布
TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints
AI总结：
TrackGS通过引入全局轨迹约束优化3D高斯点分布，实现无COLMAP的视点合成，提升渲染质量和降低姿态误差。
摘要：
我们提出了TrackGS，一种将全局特征轨迹与3D高斯点分布（3DGS）相结合的新方法，用于无COLMAP的视点合成。虽然3DGS在渲染质量上表现出色，但其对准确预计算相机参数的依赖仍然是一个显著限制。现有的无COLMAP方法依赖于局部约束，在复杂场景中效果不佳。我们的关键创新在于利用特征轨迹建立全局几何约束，从而同时优化相机参数和3D高斯点。具体来说，我们：（1）引入了受轨迹约束的高斯点作为几何锚点，（2）提出了新的2D和3D轨迹损失以强制多视图一致性，（3）推导出可微的相机内参优化公式。在具有挑战性的现实世界和合成数据集上进行的广泛实验表明，我们的方法在性能上处于最先进的水平，其姿态误差远低于以前的方法，同时保持了优越的渲染质量。我们的方法消除了对COLMAP预处理的需要，使3DGS在实际应用中更加可行。
英文摘要：
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.
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。
