LoGS: 少ない学習画像でガウススプラッティングによる視覚的自己位置推定
LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images
3Dガウススプラッティングをシーン表現に用い、画像検索と特徴マッチングで初期姿勢を推定した後、合成による解析で高精度なカメラ姿勢を求める視覚的自己位置推定手法を提案。
著者: Yuzhou Cheng, Jianhao Jiao, Yue Wang, Dimitrios Kanoulas
分類: cs.CV, cs.RO
原文アブストラクト
Visual localization involves estimating a query image's 6-DoF (degrees of freedom) camera pose, which is a fundamental component in various computer vision and robotic tasks. This paper presents LoGS, a vision-based localization pipeline utilizing the 3D Gaussian Splatting (GS) technique as scene representation. This novel representation allows high-quality novel view synthesis. During the mapping phase, structure-from-motion (SfM) is applied first, followed by the generation of a GS map. During localization, the initial position is obtained through image retrieval, local feature matching coupled with a PnP solver, and then a high-precision pose is achieved through the analysis-by-synthesis manner on the GS map. Experimental results on four large-scale datasets demonstrate the proposed approach's SoTA accuracy in estimating camera poses and robustness under challenging few-shot conditions.
