GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction
This work improves the accuracy and speed of 3D reconstruction for researchers and practitioners working with novel view synthesis and 3D scene representation, offering both COLMAP-free and high-quality variants.
This paper introduces GloSplat, a framework for joint pose-appearance optimization during 3D Gaussian Splatting training. It achieves state-of-the-art performance among COLMAP-free methods with GloSplat-F and surpasses all COLMAP-based baselines with GloSplat-A.
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.