3 papers
cs.CV2026
Uncertainty-Aware Hierarchical Re-Localization in OpenStreetMap via Semantic Alignment
Yuchen Zou, Xiao Hu, Lihuang Fang +1
Monocular re-localization enables robots to estimate camera poses from visual observations. However, many existing methods rely on dense maps or large reference image databases, wh…
cs.CV2024
Geo-ConvGRU: Geographically Masked Convolutional Gated Recurrent Unit for Bird-Eye View Segmentation
Guanglei Yang, Yongqiang Zhang, Wanlong Li +5
Convolutional Neural Networks (CNNs) have significantly impacted various computer vision tasks, however, they inherently struggle to model long-range dependencies explicitly due to…
cs.CV2023
Semi-Supervised Learning for Visual Bird's Eye View Semantic Segmentation
Junyu Zhu, Lina Liu, Yu Tang +3
Visual bird's eye view (BEV) semantic segmentation helps autonomous vehicles understand the surrounding environment only from images, including static elements (e.g., roads) and dy…