# Video synthesis of human upper body with realistic face

arXiv: https://arxiv.org/abs/1908.06607 · HTML: https://mlsanity.com/paper/1908.06607/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 4 of 4)

- [Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian](https://mlsanity.com/paper/2208.09122/) (2022)
- [Do as we do: Multiple Person Video-To-Video Transfer](https://mlsanity.com/paper/2104.04721/) (2021)
- [How Self-Supervised Learning Can be Used for Fine-Grained Head Pose Estimation?](https://mlsanity.com/paper/2108.04893/) (2021)
- [A Waste Copper Granules Rating System Based on Machine Vision](https://mlsanity.com/paper/2207.04575/) (2022)

## Abstract (arXiv)

This paper presents a generative adversarial learning-based human upper body video synthesis approach to generate an upper body video of target person that is consistent with the body motion, face expression, and pose of the person in source video. We use upper body keypoints, facial action units and poses as intermediate representations between source video and target video. Instead of directly transferring the source video to the target video, we firstly map the source person's facial action units and poses into the target person's facial landmarks, then combine the normalized upper body keypoints and generated facial landmarks with spatio-temporal smoothing to generate the corresponding target video's image. Experimental results demonstrated the effectiveness of our method.