4 papers
JSGS: JPEG State-Guided Supervision for 3D Gaussian Splatting from Mixed-Quality Views
Jinhua Cui, Anhong Wang, Kai Hu +5
Standard 3D Gaussian Splatting (3DGS) assumes that every input image faithfully samples scene radiance. However, mixed-quality JPEG images violate this assumption because compressi…
Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Clouds
Hao Jing, Anhong Wang, Yifan Zhang +2
Regarding intelligent transportation systems, low-bitrate transmission via lossy point cloud compression is vital for facilitating real-time collaborative perception among connecte…
Data-driven Camera and Lidar Simulation Models for Autonomous Driving: A Review from Generative Models to Volume Renderers
Hamed Haghighi, Xiaomeng Wang, Hao Jing +1
Perception sensors, particularly camera and Lidar, are key elements of Autonomous Driving Systems (ADS) that enable them to comprehend their surroundings to informed driving and co…
Boosting 3D Object Detection with Semantic-Aware Multi-Branch Framework
Hao Jing, Anhong Wang, Lijun Zhao +5
In autonomous driving, LiDAR sensors are vital for acquiring 3D point clouds, providing reliable geometric information. However, traditional sampling methods of preprocessing often…