/iPERCore-deepfake

Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis

Primary LanguagePythonApache License 2.0Apache-2.0

Impersonator++

Update News

See the details of developing logs.

Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis, including human motion imitation, appearance transfer, and novel view synthesis. Currently the paper is under review of IEEE TPAMI. It is an extension of our previous ICCV project impersonator, and it has a more powerful ability in generalization and produces higher-resolution results (512 x 512, 1024 x 1024) than the previous ICCV version.

๐Ÿงพ Colab Notebook Released (Windows) ๐Ÿ“‘ Paper ๐Ÿ“ฑ Website ๐Ÿ“‚ Dataset ๐Ÿ’ก Bilibili โœ’ Forum
Open In Colab [Usage] paper website Dataset bilibili Forum

Installation

See more details, including system dependencies, python requirements and setups in install.md. Please follows the instructions in install.md to install this firstly.

Notice that imags_size=512 need at least 9.8GB GPU memory. if you are using a middle-level GPU(e.g. RTX 2060), you should change the image_size to 384 or 256. The following table can be used as a reference:

image_size preprocess personalize run_imitator recommended gpu
256x256 3.1 GB 4.3 GB 1.1 GB RTX 2060 / RTX 2070
384x384 3.1 GB 7.9 GB 1.5 GB GTX 1080Ti / RTX 2080Ti / Titan Xp
512x512 3.1 GB 9.8 GB 2 GB GTX 1080Ti / RTX 2080Ti / Titan Xp
1024x1024 3.1 GB 20 GB - RTX Titan / P40 / V100 32G

Run demos

1. Run on Google Colab

Open In Colab

2. Run with Console (scripts) mode

See scripts_runner for more details.

3. Run with GUI mode

Coming soon!

Citation

@misc{liu2020liquid,
      title={Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis}, 
      author={Wen Liu and Zhixin Piao, Zhi Tu, Wenhan Luo, Lin Ma and Shenghua Gao},
      year={2020},
      eprint={2011.09055},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@InProceedings{lwb2019,
    title={Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis},
    author={Wen Liu and Zhixin Piao, Min Jie, Wenhan Luo, Lin Ma and Shenghua Gao},
    booktitle={The IEEE International Conference on Computer Vision (ICCV)},
    year={2019}
}