Home

Awesome

RangeDet in MXNet

An anchor-free single-stage LiDAR-based 3D object detector purely based on the range view representation.

This is the official implementation of RangeDet (ICCV 2021).

News

Update the KITTI results, which is also reported at our CVF access version.

Introduction

RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection [arXiv] [CVF] [Supplementary materials]

Lue Fan*, Xuan Xiong*, Feng Wang, Naiyan Wang , Zhaoxiang Zhang

*Equal contribution

We propose a pure range-view-based framework - RangeDet, which includes range conditioned pyramid, Meta-Kernel, weighted non-maximum suppression, and a iou-awared classification loss to overcome a couple of challenges in range-view-based 3D detector and achieves comparable performance with state-of-the-art multi-view-based detectors.

Quick Overview

datasets
    create_range_image_roidb.py
rangedet
    symbol
        backbone
            dla_backbone.py
            meta_kernel.py
        head
            builder.py
            loss.py
    core
        detection_metric.py
        input.py
        util_func.py
config 
    ...
scripts 
     distributed_train_and_test.sh
tools
    train.py
    test.py
    create_prediction_bin_3d.py

Some extra points and reminders:

Models Performance

Results of KITTI test split

KITTI results

Results of vehicle evaluated on WOD validation split

Experiments were performed using uniformly sample 25% training data (∼40k frames)

MethodTrain epochdata sizew/wo augOverall LEVEL 1 3D-AP/APH on Vehicle (IoU=0.7)Overall LEVEL 2 3D-AP/APH on Vehicle (IoU=0.7)
rangedet_veh_wo_aug_4_18e181/4no67.2/66.658.6/58.1
rangedet_ped_wo_aug_4_18e181/4no65.0/60.056.2/51.8
rangedet_veh_wo_aug_all_36e361/1no70.1/69.662.9/62.4
rangedet_ped_wo_aug_all_36e361/1no70.9/66.461.8/57.8

We will further add the experiment results here, for now please refer to our overall performance on Waymo leaderboard in this link .

Installation

Installing and compiling rangedet in the following command.

pip install -v -e .

We will further add requirements and installation instructions on how to install Horovod , OpenMPI and MXNet.

Training on Waymo Open Dataset

To train on the Waymo Open Dataset:

datasets
    waymo
        training/*.tfrecord
        validation/*.tfrecord
        testing/*.tfrecord

To run the python script datasets/create_range_image_roidb.py, do the following settings in the file:

python datasets/create_range_image_roidb.py --data_path  "**/datasets/waymo" --save_path "**/datasets/waymo-range" --dataset-split 'training' --save_dir 'npz_data'
datasets
    waymo-range
        training/*.roidb
        validation/*.roidb
        testing/*.roidb
        npz_data/**/*.npz

Single GPU training

Most of the configuration files that we provide assume that we are running on 8 GPUs. In order to be able to run it on fewer GPUs, there are a few possibilities:

1. Run the following

python tools/train.py --config "/path/to/config/file.py"

Multi-GPU training

./scripts/horovodrun.sh 8 "python tools/train.py --config /path/to/config/file.py"

Note you don't need to change any config between single GPU training and multi-GPU training.

Mixed precision training

To enable, just do Single-GPU or Multi-GPU training and set General.fp16 = True in the config/*.py file.

Create High-quality Range Images on KITTI

We use Hough Transformation to obtain scanning parameters following RCD. Based on the scanning parameters, it easy to create high-quality range images.

To create range images on KITTI, just simply run:

python ./datasets/create_range_image_in_kitti.py --source-dir your_source_kitti_folder --target-dir your_save_directory

We assume that the source KITTI data is in MMDetection3D format. In other words, the folder your_source_kitti_path is supposed to contains kitti_infos_trainval.pkl and kitti_infos_test.pkl. It is easy to create these files following the instruction of MMDetection3D.

Evaluation on Waymo Open Dataset

You can test your model on single gpus. Here is an example:

python tools/test.py --config "/path/to/config/file.py"

You need to create a bin file so that you can use the official waymo evaluation metrics code to get the evaluation results.

python tools/create_prediction_bin_3d.py --p "/path/to/experiments" --c "config_file" -e num_epoch --s "/path/to/save_bin_file"

Acknowledgments

This project is based on SimpleDet. Thanks Yuntao Chen and his colleagues for their great work!

Citations

Please consider citing our paper in your publications if it helps your research.

@InProceedings{Fan_2021_ICCV,
    author    = {Fan, Lue and Xiong, Xuan and Wang, Feng and Wang, Naiyan and Zhang, ZhaoXiang},
    title     = {RangeDet: In Defense of Range View for LiDAR-Based 3D Object Detection},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
}

License

RangeDet is released under the Apache license. See LICENSE for additional details.