Florian-Barthel / 3d-multiview-inversion

Official implementation of https://arxiv.org/pdf/2312.05330.pdf

Home Page:https://florian-barthel.github.io/multiview-inversion/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

3D Multiview Inversion

Project page

Prepare Video Data

Coming soon

Run Inversion

Multi-view Inversion

python multiview_inversion.py --network=path/to/pkl --target=path/to/data --num-steps=500 --num-steps_pti=500 --outdir=./out --num-targets=7

Multi-latent Inversion

python multiview_inversion_multi_w.py --network=path/to/pkl --target=path/to/data --num-steps=500 --num-steps_pti=500 --outdir=./out --num-targets=7 --continue-w=path/to/checkpoint --use-interpolation=True --depth-reg=True --w-norm-reg=True

Citation

Multiview Inversion

@misc{barthel2023multiview,
      title={Multi-view Inversion for 3D-aware Generative Adversarial Networks}, 
      author={Florian Barthel and Anna Hilsmann and Peter Eisert},
      year={2023},
      eprint={2312.05330},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

EG3D

@inproceedings{Chan2022,
  author = {Eric R. Chan and Connor Z. Lin and Matthew A. Chan and Koki Nagano and Boxiao Pan and Shalini De Mello and Orazio Gallo and Leonidas Guibas and Jonathan Tremblay and Sameh Khamis and Tero Karras and Gordon Wetzstein},
  title = {Efficient Geometry-aware {3D} Generative Adversarial Networks},
  booktitle = {CVPR},
  year = {2022}
}

Acknowledgements

This work has partly been funded by the German Research Foundation (project 3DIL, grant no. 502864329) and the German Federal Ministry of Education and Research (project VoluProf, grant no. 16SV8705).

About

Official implementation of https://arxiv.org/pdf/2312.05330.pdf

https://florian-barthel.github.io/multiview-inversion/

License:Other


Languages

Language:Python 86.4%Language:Cuda 10.3%Language:C++ 3.4%Language:HTML 0.0%