activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2025

Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting

Kyle Gao, Liangzhi Li, Hongjie He +3

Recently released open-source pre-trained foundational image segmentation and object detection models (SAM2+GroundingDINO) allow for geometrically consistent segmentation of object…

cs.CV2025

UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation

Pengfei Zhang, Chang Li, Yongjun Zhang +3

Remotely sensed imagery interpretation (RSII) faces the three major problems: (1) objective representation of spatial distribution patterns; (2) edge uncertainty problem caused by…

cs.CV2025

Digital Twin Buildings: 3D Modeling, GIS Integration, and Visual Descriptions Using Gaussian Splatting, ChatGPT/Deepseek, and Google Maps Platform

Kyle Gao, Dening Lu, Liangzhi Li +4

Urban digital twins are virtual replicas of cities that use multi-source data and data analytics to optimize urban planning, infrastructure management, and decision-making. Towards…

cs.CV2025

L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection

Xun Huang, Ziyu Xu, Hai Wu +7

LiDAR-based vision systems are integral for 3D object detection, which is crucial for autonomous navigation. However, they suffer from performance degradation in adverse weather co…

cs.CV2024

3D Learnable Supertoken Transformer for LiDAR Point Cloud Scene Segmentation

Dening Lu, Jun Zhou, Kyle Gao +2

3D Transformers have achieved great success in point cloud understanding and representation. However, there is still considerable scope for further development in effective and eff…

cs.CV2024

Efficient Point Transformer with Dynamic Token Aggregating for LiDAR Point Cloud Processing

Dening Lu, Jun Zhou, Kyle +3

Recently, LiDAR point cloud processing and analysis have made great progress due to the development of 3D Transformers. However, existing 3D Transformer methods usually are computa…