2 Hits in 5.2 sec

Reducing latency and bandwidth for video streaming using keypoint extraction and digital puppetry [article]

Roshan Prabhakar, Shubham Chandak, Carina Chiu, Renee Liang, Huong Nguyen, Kedar Tatwawadi, Tsachy Weissman
2021 arXiv   pre-print
The code for this work is available at  ...  The added computational latency due to the mesh extraction and animation is below 120ms on a standard laptop, showcasing the potential of this framework for real-time applications.  ...  Acknowledgements We thank the Stanford Compression Forum and the STEM to SHTEM high school internship program for providing us the opportunity to work on this project.  ... 
arXiv:2011.03800v2 fatcat:5nrre2iujvhnnonez44amzcy7i

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation [article]

Yuanxun Lu, Jinxiang Chai, Xun Cao
2021 arXiv   pre-print
The first stage is a deep neural network that extracts deep audio features along with a manifold projection to project the features to the target person's speech space.  ...  In the second stage, we learn facial dynamics and motions from the projected audio features.  ...  Yuanxun Lu would also like to thank Xinya Ji for her mental support and proof-reading during the project.  ... 
arXiv:2109.10595v2 fatcat:s35nqajynjeefcx67k42rpr7r4