Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
The official code of our ICCV2023 work: Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation
| Date | Stars |
|---|---|
| 2026-07-24 | 252 |
| 2026-07-25 | 252 |
| 2026-07-28 | 252 |
| 2026-07-30 | 252 |
| 2026-08-06 | 252 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
## :book: Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head Video Generation (ICCV 2023)
<p align="center">
<small>:fire: If MCNet is helpful in your photos/projects, please help to :star: it or recommend it to your friends. Thanks:fire:</small>
</p>
> [[Paper](https://arxiv.org/abs/2307.09906)   [[Project Page](https://harlanhong.github.io/publications/mcnet.html)]   [[Poster Video](https://www.youtube.com/watch?v=nahsJNjWzGo&t=1s)]<br>
<!-- > [Fa-Ting Hong](https://harlanhong.github.io), [Longhao Zhang](https://dblp.org/pid/236/7382.html), [Li Shen](https://scholar.google.co.uk/citations?user=ABbCaxsAAAAJ&hl=en), [Dan Xu](https://www.danxurgb.net) <br> -->
<!-- > The Hong Kong University of Science and Technology, Alibaba Cloud -->
> [Fa-Ting Hong](https://harlanhong.github.io), [Dan Xu](https://www.danxurgb.net) <br>
> The Hong Kong University of Science and Technology<br>
<p align="center">
<img src="assets/compare-same-id.png">
</p>
### Interesting Sample
https://github.com/harlanhong/ICCV2023-MCNET/assets/19970321/4e8af5f6-b042-4ced-af2c-93c95e1b7009
:triangular_flag_on_post: **Updates**
- :fire::fire::white_check_mark: July 20 2023: Our new talking head work **[MCNet](https://harlanhong.github.io/publications/mcnet.html)** was accpted by ICCV2023. The code will be released in ten days. You can talk a look at our previous work **[DaGAN](https://harlanhong.github.io/publications/dagan.html)** first.
## :wrench: Dependencies and Installation
- Python >= 3.7 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))
- [PyTorch >= 1.7](https://pytorch.org/)
- Option: NVIDIA GPU + [CUDA](https://developer.nvidia.com/cuda-downloads)
- Option: Linux
### Installation
We now provide a *clean* version of MCNet, which does not require customized CUDA extensions. <br>
1. Clone repo
```bash
git clone https://github.com/harlanhong/ICCV2023-MCNET.git
cd ICCV2023-MCNET
```
2. Install dependent packages
```bash
pip install -r requirements.txt
## Install the Face Alignment lib
cd face-alignment
pip install -r requirements.txt
python setup.py install
```
## :zap: Quick Inference
We take the paper version for an example. More models can be found [here](https://hkustconnect-my.sharepoint.com/:f:/g/personal/fhongac_connect_ust_hk/EjfeXuzwo3JMn7s0oOPN_q0B81P5Wgu_kbYJAh7uSAKS2w?e=KaQcPk).
### YAML configs
See ```config/vox-256.yaml``` to get description of each parameter.
### Pre-trained checkpoint
The pre-trained checkpoint of face depth network and our MCNet checkpoints can be found under following link: [OneDrive](https://hkustconnect-my.sharepoint.com/:f:/g/personal/fhongac_connect_ust_hk/Eow4kyCdz_9Ctw-Xj8cA0KwBVyh7ohx-x4-0UhgWiaSpkg?e=TOlwpa).
**Inference!**
To run a demo, download checkpoint and run the following command:
```bash
CUDA_VISIBLE_DEVICES=0 python demo.py --config config/vox-256.yaml --driving_video path/to/driving --source_image path/to/source --checkpoint path/to/checkpoint --relative --adapt_scale --kp_num 15 --generator Unet_Generator_keypoint_aware --result_video path/to/result --mbunit ExpendMemoryUnit --memsize 1
```
<!-- python demo.py --config config/vox-256.yaml --driving_video /data/fhongac/origDataset/vox1/train/id10686#zDkgVesX7NU#001423#001797.mp4 --checkpoint checkpoints/00000099-checkpoint.pth.tar --relative --adapt_scale --kp_num 15 --generator Unet_Generator_keypoint_aware --result_video synthetic_2.mp4 --source_image /data/fhongac/origDataset/vox1_frames/train/id10686#zDkgVesX7NU#001423#001797.mp4/0000000.png --mbunit ExpendMemoryUnit --memsize 1 -->
The result will be stored in ```path/to/result```. The driving videos and source images should be cropped before it can be used in our method. To obtain some semi-automatic crop suggestions you can use ```python crop-video.py --inp some_youtube_video.mp4```.Excerpt of 7,330 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:20515980916ea084, topic:animation, topic:talking-head, topic:deepfake
matched fp:20515980916ea084, topic:image-generation, topic:gan