Event
OmniVLoc: A Topological-Metric Visual Localization System for Panoramic Cameras
1 reports · 1 sources
Zhuo Yu et al. propose OmniVLoc, a visual localization system for panoramic cameras. By fusing global scene recognition with monocular depth estimation, it constructs a multi-constraint localization paradigm and solves a scale-aware pose graph and spherical bundle adjustment to recover metric-scale poses. The system includes a built-in hierarchical verification mechanism to filter erroneous outputs at each stage. The authors state that experiments on public datasets and a self-built dataset validated its accuracy and reliability, and that the source code and dataset will be released after the paper is published.
Report timeline
- OmniVLoc: A Topo-metric Visual Localization System for Omnidirectional Cameras
OmniVLoc proposes a surround-view visual localization system for omnidirectional cameras based on a topo-metric framework. It fuses global place recognition with monocular depth estimation to achieve multi-constrained localization, and solves a scale-aware pose graph and spherical bundle adjustment to recover metric-level poses. The system includes a hierarchical verification mechanism that filters erroneous outputs at each stage to improve robustness. Experiments on public datasets and a custom dataset validate its accuracy and reliability, and the source code and dataset will be released after the paper is published.
arXiv cs.RO ·