-
ONECE Dataset
A dataset for 3D object detection from LiDAR point clouds, containing 5,000 training frames and 3,000 validation frames. -
KITTI 3D Object Benchmark
A dataset for 3D object detection from LiDAR point clouds, containing 7,481 labeled samples and 3,712 training samples and 3,769 validation samples. -
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection
A proposal-level point cloud SSL framework for 3D object detection, learning robust 3D representations by contrasting region proposals.
