###Final Announcement
**Happy new year!** The competition is now closed for submission and we would announce the most realistic results for both settings once we finish all the evaluations.
**Update: The final ranking is announced and the leader of the top3 team please send a confirmation email to [gjn0310@sjtu.edu.cn]. Please also indicate your team name in the email.**


In this task, we specifically focus on the ability to generate talking heads with realistic facial expressions and natural head poses that match the accompanying audio. By learning from both the audio and visual data, this task focuses on developing a **multi-modal learning model for talking head generation**. We further design the following two settings to motivate the participants to tackle this task with 2D and 3D methods, respectively.

- **Single image setting**: Participants are allowed to train their model with external data, and we will provide a **single image** for their models to animate.

- **Video setting**: Participants are not allowed to train their model with external data, while a **video** is provided for training a personalized talking head model. Participants are allowed to use pretrained audio models to process audios but are not allowed to use pretrained talking head (visual) model and finetune under this setting.

The final output of both settings should be a talking head model that can be driven by any input audio. For the image setting, the synthesized talking head videos are expected to be lip-synchronized and with high fidelity.  As for the video setting, we encourage the participants to design 3D-based models so that the speakers can have various natural poses during talking while preserving their identity. 

The official website of the workshop is provided as https://digitalhumanworkshop.github.io/

###Prizes
1st Place - $ 1000
2nd Place - $ 500
3rd Place - $ 300
The first place of the competition would win 1000$ as the prize, the second place would win 500$ and the third place would win 300$. An additional "Most Realistic" Award would be chosen at the end of the competition by the host for both tracks. **Note that teams that win the prize should submit their code and a brief summary at the end of the competition.**

If you have any questions, please raise an issue in the discussion.

**Please check all the requirements in the submission section before you submit your results.**