Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

Code

• github.com/poodarchu/Class-balanced-Grouping-and-Sampling-for-Point-Cloud-3D-Object-Detection
  OfficialIn paperpytorch★ 0
• github.com/johnwlambert/argoverse_cbgs_kf_tracker
  none★ 0
• github.com/poodarchu/Det3D
  pytorch★ 0

Abstract

This report presents our method which wins the nuScenes3D Detection Challenge [17] held in Workshop on Autonomous Driving(WAD, CVPR 2019). Generally, we utilize sparse 3D convolution to extract rich semantic features, which are then fed into a class-balanced multi-head network to perform 3D object detection. To handle the severe class imbalance problem inherent in the autonomous driving scenarios, we design a class-balanced sampling and augmentation strategy to generate a more balanced data distribution. Furthermore, we propose a balanced group-ing head to boost the performance for the categories withsimilar shapes. Based on the Challenge results, our methodoutperforms the PointPillars [14] baseline by a large mar-gin across all metrics, achieving state-of-the-art detection performance on the nuScenes dataset. Code will be released at CBGS.

Tasks

Benchmark Results

Reproductions