https://github.com/jmliu88/HeSer

Code for Few-Shot Head Swapping in the Wild (CVPR 2022 Oral)
https://github.com/jmliu88/HeSer

Last synced: about 2 months ago
JSON representation

Code for Few-Shot Head Swapping in the Wild (CVPR 2022 Oral)

• Host: GitHub
• URL: https://github.com/jmliu88/HeSer
• Owner: jmliu88
• Created: 2022-04-22T07:52:59.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-04-28T01:41:09.000Z (over 2 years ago)
• Last Synced: 2024-07-18T02:49:59.722Z (2 months ago)
• Homepage:
• Size: 5.39 MB
• Stars: 254
• Watchers: 63
• Forks: 12
• Open Issues: 9
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Few-Shot Head Swapping in the Wild (CVPR 2022 Oral)

Changyong Shu, Hemao Wu, Hang Zhou, Jiaming Liu, Zhibin Hong, Changxing Ding, Junyu Han, Jingtuo Liu, Errui Ding, Jingdong Wang

### [Project](https://jmliu88.github.io/HeSer/) | [Paper](https://arxiv.org/abs/2204.13100) | [Demo](https://www.youtube.com/watch?v=bf2S74eFgt8)



We present the **Head Swapper (HeSer)**, which achieves few-shot head swapping in the wild through two delicately designed modules. Firstly, a Head2Head Aligner is devised to holistically migrate pose and expression information from the target to the source head by examining multi-scale information. Secondly, to tackle the challenges of skin color variations and head-background mismatches in the swapping procedure, a Head2Scene Blender is introduced to simultaneously modify facial skin color and fill mismatched gaps on the background around the head. Particularly, seamless blending is achieved with the help of a Semantic-Guided Color Reference Creation procedure and a Blending UNet. Extensive experiments demonstrate that the proposed method produces superior head swapping results on a variety of scenes.

## Code (Coming Soon)