VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR point cloud with a region proposal network (RPN), most existing efforts have focused on hand-crafted feature representations, for example, a bird's eye view projection... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Object Localization KITTI Cars Easy VoxelNet AP 89.35% # 1
3D Object Detection KITTI Cars Easy VoxelNet AP 77.47% # 14
Birds Eye View Object Detection KITTI Cars Easy VoxelNet AP 89.35 # 4
Birds Eye View Object Detection KITTI Cars Easy val VoxelNet AP 89.6 # 1
Birds Eye View Object Detection KITTI Cars Hard VoxelNet AP 77.39 # 5
Object Localization KITTI Cars Hard VoxelNet AP 77.39% # 1
3D Object Detection KITTI Cars Hard VoxelNet AP 57.73% # 14
Birds Eye View Object Detection KITTI Cars Hard val VoxelNet AP 78.57 # 1
Object Localization KITTI Cars Moderate VoxelNet AP 79.26% # 2
Birds Eye View Object Detection KITTI Cars Moderate VoxelNet AP 79.26% # 6
3D Object Detection KITTI Cars Moderate VoxelNet AP 65.11% # 15
Birds Eye View Object Detection KITTI Cars Moderate val VoxelNet AP 84.81 # 1
Birds Eye View Object Detection KITTI Cyclist Easy val VoxelNet AP 74.41 # 1
Birds Eye View Object Detection KITTI Cyclist Hard val VoxelNet AP 50.49 # 1
Birds Eye View Object Detection KITTI Cyclist Moderate val VoxelNet AP 52.18 # 1
Object Localization KITTI Cyclists Easy VoxelNet AP 66.7% # 2
3D Object Detection KITTI Cyclists Easy VoxelNet AP 61.22% # 10
Object Localization KITTI Cyclists Hard VoxelNe AP 50.55% # 2
3D Object Detection KITTI Cyclists Hard VoxelNet AP 44.37% # 10
Birds Eye View Object Detection KITTI Cyclists Moderate VoxelNet AP 54.76% # 6
Object Localization KITTI Cyclists Moderate VoxelNet AP 54.76% # 2
3D Object Detection KITTI Cyclists Moderate VoxelNet AP 48.36% # 10
Birds Eye View Object Detection KITTI Pedestrian Easy val VoxelNet AP 65.95 # 1
Birds Eye View Object Detection KITTI Pedestrian Hard val VoxelNet AP 56.98 # 1
Birds Eye View Object Detection KITTI Pedestrian Moderate val VoxelNet AP 61.05 # 1
3D Object Detection KITTI Pedestrians Easy VoxelNet AP 39.48% # 7
Object Localization KITTI Pedestrians Easy VoxelNet AP 46.13% # 2
Object Localization KITTI Pedestrians Hard VoxelNet AP 38.11% # 2
3D Object Detection KITTI Pedestrians Hard VoxelNet AP 31.51% # 7
Object Localization KITTI Pedestrians Moderate VoxelNet AP 40.74% # 2
Birds Eye View Object Detection KITTI Pedestrians Moderate VoxelNet AP 40.74% # 5
3D Object Detection KITTI Pedestrians Moderate VoxelNet AP 33.69% # 9

Methods used in the Paper