Impersonator++

Update News

• 15/04/2021, iPERCore-0.2.0, including

  • Add Training

  • Add Novel View Synthesis

  • Add Motion Imitation with bullet-time effects

  • Add Motion Imitation with multi-view outputs

  • Add Appearance Transfer

  • Add A Unified synthesizer: Motion Imitation + Appearance Transfer + Novel View Synthesis

  • Update torch 1.8+ with RTX30+ GPUs.

• 12/10/2020, iPERCore-0.1.1, supports Windows.
• 12/06/2020, iPERCore-0.1, all the base codes. The motion imitation scripts.

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.

🧾 Colab Notebook	📑 Paper	📱 Website	📂 Dataset	💡 Bilibili
	paper	website	Dataset	bilibili

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:

Run demos

1. Run on Google Colab

2. Run with Console (scripts) mode

See scripts_runner for more details.

Citation

@article{liu2021liquid,
  title={Liquid warping GAN with attention: A unified framework for human image synthesis},
  author={Liu, Wen and Piao, Zhixin and Tu, Zhi and Luo, Wenhan and Ma, Lin and Gao, Shenghua},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2021},
  publisher={IEEE}
}

@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}
}