IJCAI 2022poster1 citations

Real-Time Portrait Stylization on the Edge

Yanyu Li, Xuan Shen, Geng Yuan, Jiexiong Guan, Wei Niu, Hao Tang, Bin Ren, Yanzhi Wang

Abstract

In this work we demonstrate real-time portrait stylization, specifically, translating self-portrait into cartoon or anime style on mobile devices. We propose a latency-driven differentiable architecture search method, maintaining realistic generative quality. With our framework, we obtain 10× computation reduction on the generative model and achieve real-time video stylization on off-the-shelf smartphone using mobile GPUs.

Computer Vision: Neural generative models, auto encoders, GANsConstraint Satisfaction and Optimization: ApplicationsMachine Learning: Automated Machine Learning
BibTeX
@inproceedings{ijcai2022p856,
  title     = {Real-Time Portrait Stylization on the Edge},
  author    = {Li, Yanyu and Shen, Xuan and Yuan, Geng and Guan, Jiexiong and Niu, Wei and Tang, Hao and Ren, Bin and Wang, Yanzhi},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-22}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {5928--5931},
  year      = {2022},
  month     = {7},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2022/856},
  url       = {https://doi.org/10.24963/ijcai.2022/856},
}
Real-Time Portrait Stylization on the Edge · IJCAI 2022