GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction

TL;DR

GloSplat introduces a joint pose-appearance optimization framework for 3D reconstruction that maintains explicit feature tracks, leading to faster and more accurate results compared to prior methods.

Contribution

It presents a novel joint optimization approach that preserves explicit SfM feature tracks during 3D Gaussian Splatting training, preventing pose drift and improving accuracy.

Findings

GloSplat-F achieves state-of-the-art results among COLMAP-free methods.

GloSplat-A surpasses all COLMAP-based baselines.

Joint optimization with explicit feature tracks enhances 3D reconstruction quality.

Abstract

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.