8 papers · 1 filter
Scene Reconstruction as Mapping Priors for 3D Detection
Yang Fu, Yuliang Zou, Hao Xiang +8
In autonomous driving, mapping is critical for motion planning but remains an under-utilized resource for perception tasks such as 3D object detection. Maps can provide robust stru…
STELLAR: Scaling 3D Perception Large Models for Autonomous Driving
Yingwei Li, Xin Huang, Yang Liu +13
Model scaling has demonstrated remarkable success through large-scale training on diverse datasets. It remains an open question whether the same paradigm would apply to autonomous…
BioHuman: Learning Biomechanical Human Representations from Video
Yujun Huo, He Zhang, Chentao Song +3
Understanding human motion beyond surface kinematics is crucial for motion analysis, rehabilitation, and injury risk assessment. However, progress in this domain is limited by the…
MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images
Chentao Song, He Zhang, Haolei Yuan +4
We introduce MetricHMSR, a novel framework for recovering metric human meshes and 3D scenes from a single monocular image. Existing methods struggle to recover metric scale due to…
Multi-View Representation is What You Need for Point-Cloud Pre-Training
Siming Yan, Chen Song, Youkang Kong +1
A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. Th…
LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation
Haitao Yang, Zaiwei Zhang, Xiangru Huang +5
Bird's-Eye View (BEV) features are popular intermediate scene representations shared by the 3D backbone and the detector head in LiDAR-based object detectors. However, little resea…