Home

Awesome

SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation (3DV 2022)

<p align="center"> <img src ="assets/sc6d_overview.png" width="800" /> </p>
@inproceedings{cai2022sc6d,
  title={SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation},
  author={Cai, Dingding and Heikkil{\"a}, Janne and Rahtu, Esa},
  booktitle={2022 International Conference on 3D Vision (3DV)},
  year={2022},
  organization={IEEE}
}

Setup

Please start by installing Miniconda3 with Pyhton3.8 or above.

git clone https://github.com/dingdingcai/SC6D-pose.git
cd SC6D-pose
conda env create -f environment.yml
conda activate sc6d
pip install torch==1.8.0+cu111 torchvision==0.9.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html
pip install "git+https://github.com/facebookresearch/pytorch3d.git"
python -m pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu111/torch1.8/index.html

Dataset

Our evaluation is conducted on three benchmark datasets all downloaded from BOP website. All three datasets are stored in the same directory, e.g. BOP_Dataset/tless, BOP_Dataset/ycbv, BOP_Dataset/itodd, and set the "DATASET_ROOT" (in config.py) to the BOP_Dataset directory.

Denpendencies

This project requires the evaluation code from bop_toolkit.

Pre-trained Models

The pre-trained models can be downloaded here, all the models are saved to the checkpoints directory, for example, checkpoints/tless, checkpoints/ycbv, checkpoints/itodd.

Inference

Download the predicted detection results from BOP Challenge 2022 and decompress it to the root directory.

Evaluation on the model trained using only PBR images.

Evaluation on the model first trained using the PBR images and finetuned with the combined Synt+Real images

Training

To train SC6D, download the VOC2012 dataset and set the "VOC_BG_ROOT" (in config.py) to the VOC2012 directory

Acknowledgement