6 papers
VFM-Loc: Training-Free Cross-View Geo-Localization via Aligning Discriminative Visual Hierarchies
Jun Lu, Zehao Sang, Haoqi Wei +5
Cross-View Geo-Localization (CVGL) in remote sensing aims to locate a drone-view query by matching it to geo-tagged satellite images. Although supervised methods have achieved stro…
SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts
Haida Feng, Hao Wei, Haolin Wang +3
Recent Multimodal Large Language Models (MLLMs) struggle to bridge the representational gap between 2D semantic understanding and 3D spatial geometry. Existing 3D-aware models eith…
Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views
Haida Feng, Hao Wei, Zewen Xu +3
Recently, large language models (LLMs) have been explored widely for 3D scene understanding. Among them, training-free approaches are gaining attention for their flexibility and ge…
Floorplan-SLAM: A Real-Time, High-Accuracy, and Long-Term Multi-Session Point-Plane SLAM for Efficient Floorplan Reconstruction
Haolin Wang, Zeren Lv, Hao Wei +2
Floorplan reconstruction provides structural priors essential for reliable indoor robot navigation and high-level scene understanding. However, existing approaches either require t…
An Accurate and Real-time Relative Pose Estimation from Triple Point-line Images by Decoupling Rotation and Translation
Zewen Xu, Yijia He, Hao Wei +3
Line features are valid complements for point features in man-made environments. 3D-2D constraints provided by line features have been widely used in Visual Odometry (VO) and Struc…
DOGE: An Extrinsic Orientation and Gyroscope Bias Estimation for Visual-Inertial Odometry Initialization
Zewen Xu, Yijia He, Hao Wei +1
Most existing visual-inertial odometry (VIO) initialization methods rely on accurate pre-calibrated extrinsic parameters. However, during long-term use, irreversible structural def…