Code for "VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations", ICCV 2023. [Arxiv]
Created by Jiehong Lin, Zewei Wei, Yabin Zhang, Kui Jia.
The code has been tested with
- python 3.7.6
- pytorch 1.9.0
- CUDA 11.3
Other dependencies:
sh dependencies.sh
Please refer to our another work of Self-DPDN.
The trained models and test results are provided here.
Train VI-Net for rotation estimation:
python train.py --gpus 0 --dataset ${DATASET} --mode r
Train the network of pointnet++ for translation and size estimation:
python train.py --gpus 0 --dataset ${DATASET} --mode ts
The string "DATASET" could be set as DATASET=REAL275
or DATASET=CAMERA25
.
To test the model, please run:
python test.py --gpus 0 --dataset ${DATASET}
The string "DATASET" could be set as DATASET=REAL275
or DATASET=CAMERA25
.
If you find our work useful in your research, please consider citing:
@inproceedings{lin2023vi,
title={Vi-net: Boosting category-level 6d object pose estimation via learning decoupled rotations on the spherical representations},
author={Lin, Jiehong and Wei, Zewei and Zhang, Yabin and Jia, Kui},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={14001--14011},
year={2023}
}
Our implementation leverages the code from NOCS, DualPoseNet, and SPD.
Our code is released under MIT License (see LICENSE file for details).
mortimer.jh.lin@gmail.com