V2AI/Det3D

V2AI/Det3D has 1,565 GitHub stars and 289 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-12 03:05 UTC. Last push 2023-12-19.

Comment ces chiffres sont mesurés

World's first general purpose 3D object detection codebse.

1,565 étoiles 289 forks

Progression mesurée des étoiles

in 24h: 0
in 7 days: 0
in 15 days: Mise à jour retardée
in 1 month: Mise à jour retardée

Variations nettes sur des périodes qui se chevauchent, pas des totaux quotidiens. Les mesures absentes restent vides. Les étoiles indiquent l’intérêt, pas la qualité.

README.md

Original

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

	mAP	mATE	mASE	mAOE	mAVE	mAAE	NDS	ckpt
CBGS	49.9	0.335	0.256	0.323	0.251	0.197	61.3	link
PointPillar	41.8	0.363	0.264	0.377	0.288	0.198	56.0	link

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}
}