6 papers
GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss
Yangfan Xu, Lilian Zhang, Xiaofeng He +3
Transformer-based general visual geometry frameworks have shown promising performance in camera pose estimation and 3D scene understanding. Recent advancements in Visual Geometry G…
VGC-RIO: A Tightly Integrated Radar-Inertial Odometry with Spatial Weighted Doppler Velocity and Local Geometric Constrained RCS Histograms
Jianguang Xiang, Xiaofeng He, Zizhuo Chen +3
Recent advances in 4D radar-inertial odometry have demonstrated promising potential for autonomous lo calization in adverse conditions. However, effective handling of sparse and no…
SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images
Yangfan Xu, Qu Hao, Lilian Zhang +4
Visual SLAM is essential for mobile robots, drone navigation, and VR/AR, but traditional RGB camera systems struggle in low-light conditions, driving interest in thermal SLAM, whic…
DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking and Loop-Closing
Hao Qu, Lilian Zhang, Jun Mao +5
The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. Although deep le…
SelfOdom: Self-supervised Egomotion and Depth Learning via Bi-directional Coarse-to-Fine Scale Recovery
Hao Qu, Lilian Zhang, Xiaoping Hu +3
Accurately perceiving location and scene is crucial for autonomous driving and mobile robots. Recent advances in deep learning have made it possible to learn egomotion and depth fr…
A 2D Georeferenced Map Aided Visual-Inertial System for Precise UAV Localization
Jun Mao, Lilian Zhang, Xiaofeng He +2
Precise geolocalization is crucial for unmanned aerial vehicles (UAVs). However, most current deployed UAVs rely on the global navigation satellite systems (GNSS) or high precision…