Skip to content

Latest commit

 

History

History
45 lines (30 loc) · 1.22 KB

README.md

File metadata and controls

45 lines (30 loc) · 1.22 KB
Raw

Requirements

  • Python 2.7/3.5/3.6 (If you want to use Python2.7 to run this repo, please rebuild the lib/knn/ (with PyTorch 0.4.1).)
  • PyTorch 0.4.1 (PyTroch 1.0 branch)
  • PIL
  • scipy
  • numpy
  • pyyaml
  • logging
  • matplotlib
  • CUDA 7.5/8.0/9.0 (Required. CPU-only will lead to extreme slow training speed because of the loss calculation of the symmetry objects (pixel-wise nearest neighbour loss).)

weight

baidu cloud fht0

usage

Please refer DenseFusion for usage.

Citations

Please cite MixedFusion if you use this repository in your publications:

@INPROCEEDINGS{9412494,
  author={Feng, Hangtao and Zhang, Lu and Yang, Xu and Liu, Zhiyong},
  booktitle={2020 25th International Conference on Pattern Recognition (ICPR)}, 
  title={MixedFusion: 6D Object Pose Estimation from Decoupled RGB-Depth Features}, 
  year={2021},
  volume={},
  number={},
  pages={685-691},
  doi={10.1109/ICPR48806.2021.9412494}}
}

License

Licensed under the MIT License