Saved in:
Bibliographic Details
Main Authors: Xiong, Tianyu, Li, Rui, Li, Linjie, Yang, Jiaqi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.04847
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908867414196224
author Xiong, Tianyu
Li, Rui
Li, Linjie
Yang, Jiaqi
author_facet Xiong, Tianyu
Li, Rui
Li, Linjie
Yang, Jiaqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_04847
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction
Xiong, Tianyu
Li, Rui
Li, Linjie
Yang, Jiaqi
Computer Vision and Pattern Recognition
Graphics
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.
title GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2603.04847