GloSplat：面向更快速和更精确3D重建的联合姿态-外观优化
GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction
AI总结：
GloSplat通过联合姿态-外观优化提升3D重建速度和精度，提供无COLMAP和详尽匹配两种变体，实现高效且高质量的重建效果。
摘要：
特征提取、匹配、结构从运动（SfM）和新视角合成（NVS）传统上被视为独立问题，具有独立的优化目标。我们提出了GloSplat，一个在3D高斯点划训练过程中执行联合姿态-外观优化的框架。与以往的联合优化方法（BARF、NeRF--、3RGS）不同，这些方法仅依赖于光度梯度进行姿态细化，而GloSplat保留了显式的SfM特征轨迹作为首要实体在整个训练过程中：轨迹3D点被保持为独立于高斯原语的可优化参数，通过与光度监督同时操作的重投影损失提供持久的几何锚点。这种架构选择防止了早期阶段的姿态漂移，同时使细粒度的优化成为可能——这是光度方法所缺乏的能力。我们介绍了两种流水线变体：（1）GloSplat-F，一种无COLMAP的变体，使用基于检索的配对选择进行高效重建；（2）GloSplat-A，一种详尽匹配的变体，用于最大质量。两者均采用全局SfM初始化，随后在3DGS训练过程中进行联合光度-几何优化。实验表明，GloSplat-F在无COLMAP方法中达到最先进水平，而GloSplat-A超越了所有基于COLMAP的基线。
英文摘要：
Feature extraction, matching, structure from motion (SfM), and novel view synthesis (NVS) have traditionally been treated as separate problems with independent optimization objectives. We present GloSplat, a framework that performs \emph{joint pose-appearance optimization} during 3D Gaussian Splatting training. Unlike prior joint optimization methods (BARF, NeRF--, 3RGS) that rely purely on photometric gradients for pose refinement, GloSplat preserves \emph{explicit SfM feature tracks} as first-class entities throughout training: track 3D points are maintained as separate optimizable parameters from Gaussian primitives, providing persistent geometric anchors via a reprojection loss that operates alongside photometric supervision. This architectural choice prevents early-stage pose drift while enabling fine-grained refinement -- a capability absent in photometric-only approaches. We introduce two pipeline variants: (1) \textbf{GloSplat-F}, a COLMAP-free variant using retrieval-based pair selection for efficient reconstruction, and (2) \textbf{GloSplat-A}, an exhaustive matching variant for maximum quality. Both employ global SfM initialization followed by joint photometric-geometric optimization during 3DGS training. Experiments demonstrate that GloSplat-F achieves state-of-the-art among COLMAP-free methods while GloSplat-A surpasses all COLMAP-based baselines.
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。
