STD: Sparse-to-Dense 3D Object Detector for Point Cloud

ICCV 2019 Zetong YangYanan SunShu LiuXiaoyong ShenJiaya Jia

We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point cloud as input to generate accurate proposals by seeding each point with a new spherical anchor... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Object Detection KITTI Cars Easy STD AP 86.61% # 5
Birds Eye View Object Detection KITTI Cars Easy STD AP 89.66 # 3
3D Object Detection KITTI Cars Hard STD AP 76.06% # 2
Birds Eye View Object Detection KITTI Cars Hard STD AP 86.89 # 1
Birds Eye View Object Detection KITTI Cars Moderate STD AP 87.76% # 2
3D Object Detection KITTI Cars Moderate STD AP 77.63% # 4
3D Object Detection KITTI Cyclists Easy STD AP 78.89% # 3
Birds Eye View Object Detection KITTI Cyclists Easy STD AP 81.04 # 2
3D Object Detection KITTI Cyclists Hard STD AP 55.77% # 4
Birds Eye View Object Detection KITTI Cyclists Hard STD AP 57.85 # 2
Birds Eye View Object Detection KITTI Cyclists Moderate STD AP 65.32% # 2
3D Object Detection KITTI Cyclists Moderate STD AP 62.53% # 4
Birds Eye View Object Detection KITTI Pedestrians Easy STD AP 60.99 # 1
3D Object Detection KITTI Pedestrians Easy STD AP 53.08% # 3
Birds Eye View Object Detection KITTI Pedestrians Hard STD AP 45.89 # 1
3D Object Detection KITTI Pedestrians Hard STD AP 41.97% # 3
Birds Eye View Object Detection KITTI Pedestrians Moderate STD AP 51.39% # 1
3D Object Detection KITTI Pedestrians Moderate STD AP 44.24% # 4

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet