6 papers
TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object Detection
Chenyang Lei, Weiyuan Peng, Guang Zhou +4
Most autonomous driving (AD) datasets incur substantial costs for collection and labeling, inevitably yielding a plethora of low-quality and redundant data instances, thereby compr…
ClimateGS: Real-Time Climate Simulation with 3D Gaussian Style Transfer
Yuezhen Xie, Meiying Zhang, Qi Hao
Adverse climate conditions pose significant challenges for autonomous systems, demanding reliable perception and decision-making across diverse environments. To better simulate the…
SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments
Yinqi Chen, Meiying Zhang, Qi Hao +1
Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, tr…
BiTrack: Bidirectional Offline 3D Multi-Object Tracking Using Camera-LiDAR Data
Kemiao Huang, Yinqi Chen, Meiying Zhang +1
Compared with real-time multi-object tracking (MOT), offline multi-object tracking (OMOT) has the advantages to perform 2D-3D detection fusion, erroneous link correction, and full…
SSF-PAN: Semantic Scene Flow-Based Perception for Autonomous Navigation in Traffic Scenarios
Yinqi Chen, Meiying Zhang, Qi Hao +1
Vehicle detection and localization in complex traffic scenarios pose significant challenges due to the interference of moving objects. Traditional methods often rely on outlier exc…
CTS: Sim-to-Real Unsupervised Domain Adaptation on 3D Detection
Meiying Zhang, Weiyuan Peng, Guangyao Ding +3
Simulation data can be accurately labeled and have been expected to improve the performance of data-driven algorithms, including object detection. However, due to the various domai…