Skip to content

Latest commit

 

History

History
64 lines (58 loc) · 2.54 KB

README.md

File metadata and controls

64 lines (58 loc) · 2.54 KB

ARtNet - An FFB6D Version with custom dataset for iPad

This is an unofficial source code and a modified version of FFB6D: A Full Flow Biderectional Fusion Network for 6D Pose Estimation. (Arxiv, Video_Bilibili, Video_YouTube)

@InProceedings{He_2021_CVPR,
author = {He, Yisheng and Huang, Haibin and Fan, Haoqiang and Chen, Qifeng and Sun, Jian},
title = {FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021}
}

@InProceedings{He_2020_CVPR,
author = {He, Yisheng and Sun, Wei and Huang, Haibin and Liu, Jianran and Fan, Haoqiang and Sun, Jian},
title = {PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

Installation

  • Install nvidia drive3r version compatible with cuda toolkit >= 10.2

  • Install conda environment:

    pip install conda
conda config --add channels conda-forge
conda config --add channels ramonaoptics
conda create ––name ffb6d python=3.6
conda activate ffb6d

  • Install requirements.txt and Cuda Toolkit GPU with conda & mamba:

    conda install -c menpo opencv3
conda install mamba
mamba install pytorch torchvision cudatoolkit=11.3 -c pytorch
cat requirement.txt | xargs -n 1 mamba install
pip install "pybind11[global]"

  • Install apex:

    git clone https://github.com/NVIDIA/apex
cd apex
export TORCH_CUDA_ARCH_LIST="6.0;6.1;6.2;7.0;7.5"  # set the target architecture manually, suggested in issue https://github.com/NVIDIA/apex/issues/605#issuecomment-554453001
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
cd ..

  • Install normalSpeed, a fast and light-weight normal map estimator:

    git clone https://github.com/hfutcgncas/normalSpeed.git
cd normalSpeed/normalSpeed
python setup.py install --user
cd ..

  • Install tkinter through sudo apt install python3-tk

  • Compile RandLA-Net operators:

    cd ffb6d/models/RandLA/
sh compile_op.sh

For more Information please see the official source code!