4 papers · 1 filter
G2IA: Geometry-Guided Instance-Aware Retrieval and Refinement for Cross-Modal Place Recognition
Xianyun Jiao, Jingyi Xu, Zhongmiao Yan +2
Cross-modal place recognition (CMPR) enables camera-only robots to localize against pre-built LiDAR maps in autonomous navigation scenarios. This image-to-point-cloud setting is ch…
360-GeoGS: Geometrically Consistent Feed-Forward 3D Gaussian Splatting Reconstruction for 360 Images
Jiaqi Yao, Zhongmiao Yan, Jingyi Xu +3
3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints…
XGrid-Mapping: Explicit Implicit Hybrid Grid Submaps for Efficient Incremental Neural LiDAR Mapping
Zeqing Song, Zhongmiao Yan, Junyuan Deng +5
Large-scale incremental mapping is fundamental to the development of robust and reliable autonomous systems, as it underpins incremental environmental understanding with sequential…
Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting
Jingyi Xu, Xieyuanli Chen, Junyi Ma +4
The task of occupancy forecasting (OCF) involves utilizing past and present perception data to predict future occupancy states of autonomous vehicle surrounding environments, which…