Center-based 3D Object Detection and Tracking

19 Jun 2020 Tianwei Yin Xingyi Zhou Philipp Krähenbühl

Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with additional challenges... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Multi-Object Tracking nuScenes CenterPoint-Single amota 0.64 # 9
3D Object Detection nuScenes CenterPoint NDS 0.71 # 2
mAP 0.67 # 2
mATE 0.25 # 62
mASE 0.24 # 49
mAOE 0.35 # 59
mAVE 0.25 # 56
mAAE 0.14 # 28
3D Object Detection waymo all_ns CenterPoint APH/L2 71.93 # 1
3D Object Detection waymo cyclist CenterPoint APH/L2 71.28 # 1
3D Object Detection waymo pedestrian CenterPoint APH/L2 71.52 # 1

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