Local Consistency Guidance: Personalized Stylization Method of Face Video (Student Abstract)

Wancheng Feng, Yingchao Liu, Jiaming Pei, Wenxuan Liu, Chunpeng Tian, Lukun Wang

AAAI 2024 pp. 23486-23487

doi:10.1609/AAAI.V38I21.30440 /aaai/2024/feng2024aaai-local/

Abstract

Face video stylization aims to convert real face videos into specified reference styles. While one-shot methods perform well in single-image stylization, ensuring continuity between frames and retaining the original facial expressions present challenges in video stylization. To address these issues, our approach employs a personalized diffusion model with pixel-level control. We propose Local Consistency Guidance(LCG) strategy, composed of local-cross attention and local style transfer, to ensure temporal consistency. This framework enables the synthesis of high-quality stylized face videos with excellent temporal continuity.

PDF AAAI Semantic Scholar

Cite

Text

Feng et al. "Local Consistency Guidance: Personalized Stylization Method of Face Video (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30440

Markdown

[Feng et al. "Local Consistency Guidance: Personalized Stylization Method of Face Video (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/feng2024aaai-local/) doi:10.1609/AAAI.V38I21.30440

BibTeX

@inproceedings{feng2024aaai-local,
  title     = {{Local Consistency Guidance: Personalized Stylization Method of Face Video (Student Abstract)}},
  author    = {Feng, Wancheng and Liu, Yingchao and Pei, Jiaming and Liu, Wenxuan and Tian, Chunpeng and Wang, Lukun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23486-23487},
  doi       = {10.1609/AAAI.V38I21.30440},
  url       = {https://mlanthology.org/aaai/2024/feng2024aaai-local/}
}