GeoFlow: Real-Time Fine-Grained Cross-View Geolocalization via Iterative Flow Prediction
GeoFlow:通过迭代流预测实现实时细粒度跨视角地理定位
机构 * Vermont Artificial Intelligence Lab, Department of Computer Science, University of Vermont(佛蒙特人工智能实验室,计算机科学系,佛蒙特大学) ; Intelligent Machines Lab, Information Technology University(智能机器实验室,信息科技大学) ; Institute of Artificial Intelligence, University of Central Florida(人工智能研究所,佛罗里达中央大学)
AI总结 本文提出GeoFlow,通过迭代流预测实现实时细粒度跨视角地理定位,解决了高精度与实时性的平衡问题,实验显示其在KITTI和VIGOR数据集上达到实时29FPS且保持高精度。
Comments Accepted at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)