GALoc：用于无深度单目平面图定位的重力对齐线框
GALoc: Gravity Aligned Wireframes for Depth-Free Monocular Floorplan Localization
- GIST（光州科学技术院）
- KAIST（韩国科学技术院）
- Zurich University of Applied Sciences（苏黎世应用科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
GALoc提出几何优先的无深度单目平面图定位框架，利用重力对齐线框和全局搜索优化，在可见墙体时超越深度基线，并能在结构盲场景弃权。
AI中文摘要：
平面图是紧凑且外观不变的室内定位理想地图，然而现有方法依赖在杂乱场景中脆弱的深度网络。我们提出GALoc，一种几何优先框架，用重力对齐线框替代深度预测，这些线框通过构造满足垂直性和共面性。给定单目RGB、相机内参、相对位姿和IMU方向，GALoc构建一个编码垂直性和共面性的线性约束矩阵，并通过全局搜索找到最小化其最小奇异值的相机规范。校正后的线框通过闭式、FOV一致的变换投影到鸟瞰图布局中，并通过无度量SE(2)搜索与平面图匹配。我们在Structured3D上评估端到端性能，在Gibson上使用校准噪声，并在真实世界作者收集的序列上评估。当足够的墙体几何可见时，GALoc匹配或超越基于深度的基线——在Gibson上100步序列中实现88%的0.1m顺序定位成功率，而基线为68%——同时在结构盲场景中弃权（不执行）。
英文摘要：
Floorplans are compact, appearance-invariant maps ideal for indoor localization, yet existing methods rely on depth networks that are brittle in cluttered scenes. We propose GALoc, a geometry-first framework that replaces depth prediction with gravity-aligned wireframes that satisfy verticality and coplanarity by construction. Given monocular RGB, camera intrinsics, relative poses, and IMU orientation, GALoc constructs a linear constraint matrix encoding verticality and coplanarity, and finds the camera gauge minimizing its smallest singular value via global search. The rectified wireframes are projected into bird's-eye-view layouts through a closed-form, FOV-consistent transformation and matched against the floorplan via metric-free SE(2) search. We evaluate end-to-end on Structured3D, with calibrated noise on Gibson, and on real-world author-collected sequences. When sufficient wall geometry is visible, GALoc matches or outperforms depth-based baselines -- achieving 88% sequential localization success at 0.1m over 100-step sequences on Gibson vs the baseline's 68% -- while abstaining in structure-blind scenes.
