Det3D

A general 3D Object Detection codebase in PyTorch.

1. Introduction

Det3D is the first 3D Object Detection toolbox which provides off the box implementations of many 3D object detection algorithms such as PointPillars, SECOND, PIXOR, etc, as well as state-of-the-art methods on major benchmarks like KITTI(ViP) and nuScenes(CBGS). Key features of Det3D include the following aspects:

• Multi Datasets Support: KITTI, nuScenes, Lyft
• Point-based and Voxel-based model zoo
• State-of-the-art performance
• DDP & SyncBN

2. Installation

Please refer to INSTALATION.md.

3. Quick Start

Please refer to GETTING_STARTED.md.

4. Model Zoo

4.1 nuScenes

The original model and prediction files are available in the CBGS README.

4.2 KITTI

Second on KITTI(val) Dataset

car  AP @0.70, 0.70,  0.70:
bbox AP:90.54, 89.35, 88.43
bev  AP:89.89, 87.75, 86.81
3d   AP:87.96, 78.28, 76.99
aos  AP:90.34, 88.81, 87.66

PointPillars on KITTI(val) Dataset

car  [email protected],  0.70,  0.70:
bbox AP:90.63, 88.86, 87.35
bev  AP:89.75, 86.15, 83.00
3d   AP:85.75, 75.68, 68.93
aos  AP:90.48, 88.36, 86.58

4.3 Lyft

• Lyft Config

4.4 Waymo

5. Functionality

• Models
  • VoxelNet
  • SECOND
  • PointPillars
• Features
  • Multi task learning & Multi-task Learning
  • Distributed Training and Validation
  • SyncBN
  • Flexible anchor dimensions
  • TensorboardX
  • Checkpointer & Breakpoint continue
  • Self-contained visualization
  • Finetune
  • Multiscale Training & Validation
  • Rotated RoI Align

6. TODO List

• To Be Released

  • CGBS on Lyft(val) Dataset

• Models

  • PointRCNN
  • PIXOR

7. Call for contribution.

• Support Waymo Dataset.
• Add other 3D detection / segmentation models, such as VoteNet, STD, etc.

8. Developers

Benjin Zhu , Bingqi Ma

9. License

Det3D is released under the Apache licenes.

10. Citation

Det3D is a derivative codebase of CBGS, if you find this work useful in your research, please consider cite:

@article{zhu2019class,
  title={Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection},
  author={Zhu, Benjin and Jiang, Zhengkai and Zhou, Xiangxin and Li, Zeming and Yu, Gang},
  journal={arXiv preprint arXiv:1908.09492},
  year={2019}
}

11. Acknowledgement

• mmdetection
• mmcv
• second.pytorch
• maskrcnn_benchmark