Son-Goku-gpu/detr3d

Object DGCNN & DETR3D

This repo contains the implementations of Object DGCNN (https://arxiv.org/abs/2110.06923) and DETR3D (https://arxiv.org/abs/2110.06922). Our implementations are built on top of MMdetection3D.

Prerequisite

1. mmcv (https://github.com/open-mmlab/mmcv)

2. mmdet (https://github.com/open-mmlab/mmdetection)

3. mmseg (https://github.com/open-mmlab/mmsegmentation)

4. mmdet3d (https://github.com/open-mmlab/mmdetection3d)

Data

1. Follow the mmdet3d to process the data.

Train

1. Downloads the pretrained backbone weights to pretrained/

2. For example, to train Object-DGCNN with pillar on 8 GPUs, please use

tools/dist_train.sh projects/configs/obj_dgcnn/pillar.py 8

Evaluation using pretrained models

1. Download the weights accordingly.

Backbone	mAP	NDS	Download
DETR3D, ResNet101 w/ DCN	34.7	42.2	model | log
above, + CBGS	34.9	43.4	model | log
DETR3D, VoVNet on trainval, evaluation on test set	41.2	47.9	model | log

Backbone	mAP	NDS	Download
Object DGCNN, pillar	53.2	62.8	model | log
Object DGCNN, voxel	58.6	66.0	model | log

2. To test, use
   tools/dist_test.sh projects/configs/obj_dgcnn/pillar_cosine.py /path/to/ckpt 8 --eval=bbox

If you find this repo useful for your research, please consider citing the papers

@inproceedings{
   obj-dgcnn,
   title={Object DGCNN: 3D Object Detection using Dynamic Graphs},
   author={Wang, Yue and Solomon, Justin M.},
   booktitle={2021 Conference on Neural Information Processing Systems ({NeurIPS})},
   year={2021}
}

@inproceedings{
   detr3d,
   title={DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries},
   author={Wang, Yue and Guizilini, Vitor and Zhang, Tianyuan and Wang, Yilun and Zhao, Hang and and Solomon, Justin M.},
   booktitle={The Conference on Robot Learning ({CoRL})},
   year={2021}
}