Search Results for author: Jinxiang Chai

Found 4 papers, 2 papers with code

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation

1 code implementation22 Sep 2021 Yuanxun Lu, Jinxiang Chai, Xun Cao

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.

Image-to-Image Translation Talking Face Generation +2

Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images

no code implementations22 Jun 2021 Liguo Jiang, Miaopeng Li, Jianjie Zhang, Congyi Wang, Juntao Ye, Xinguo Liu, Jinxiang Chai

We show the system advances the frontier of 3D human body and pose reconstruction from single images by quantitative evaluations and comparisons with state-of-the-art methods.

Foreground Segmentation

Music2Dance: DanceNet for Music-driven Dance Generation

no code implementations2 Feb 2020 Wenlin Zhuang, Congyi Wang, Siyu Xia, Jinxiang Chai, Yangang Wang

Synthesize human motions from music, i. e., music to dance, is appealing and attracts lots of research interests in recent years.

Motion Synthesis

Cannot find the paper you are looking for? You can Submit a new open access paper.