no code implementations • 5 Dec 2023 • Bo Ding, Zhenfeng Fan, Shuang Yang, Shihong Xia
We incorporate personalized prior in a monocular video and morphable prior in 3D face morphable space for generating personalized details under novel controllable parameters.
1 code implementation • ICCV 2023 • Boyuan Jiang, Lei Hu, Shihong Xia
The key idea is to use a probability distribution to model the camera pose and iteratively update the distribution from 2D features instead of using camera pose.
1 code implementation • ICCV 2023 • Chongyang Zhong, Lei Hu, Zihao Zhang, Shihong Xia
The latter is from the cross-modal perspective, which is used to learn the sentence-level and word-level motion-text cross-modal relationship.
Ranked #10 on Motion Synthesis on HumanML3D
1 code implementation • ICCV 2023 • Zhenfeng Fan, Zhiheng Zhang, Shuang Yang, Chongyang Zhong, Min Cao, Shihong Xia
We propose a learning framework for 3D facial attribute translation to relieve these limitations.
1 code implementation • 13 Jun 2023 • Lei Hu, Zihao Zhang, Chongyang Zhong, Boyuan Jiang, Shihong Xia
Moreover, we also show that our framework can generate reasonable results even for a more challenging retargeting scenario, like retargeting between bipedal and quadrupedal skeletons because of the body part retargeting strategy and PAN.
no code implementations • CVPR 2022 • Chongyang Zhong, Lei Hu, Zihao Zhang, Yongjing Ye, Shihong Xia
However, considering the variants and diverse action types in human motion data, the cross-dependency of the spatio-temporal relationships will be difficult to depict due to the decoupled modeling strategy, which may also exacerbate the problem of insufficient generalization.
1 code implementation • 23 Sep 2021 • Zhenfeng Fan, Silong Peng, Shihong Xia
This method is then extended to 3D surface by formulating a local registration problem for dividing and a linear least-square problem for diffusing, with constraints on fixed features.
1 code implementation • the Thirtieth International Joint Conference on Artificial Intelligence 2021 • Zihao Zhang, Lei Hu, Xiaoming Deng, Shihong Xia
In this paper, we present a new perspective on the 3D human pose estimation method from point cloud sequences.
Ranked #1 on Pose Estimation on ITOP front-view
no code implementations • 25 Apr 2021 • Qianyun Wang, Zhenfeng Fan, Shihong Xia
Impressive progress has been made in audio-driven 3D facial animation recently, but synthesizing 3D talking-head with rich emotion is still unsolved.
no code implementations • 4 Dec 2020 • Jie Yang, Lin Gao, Qingyang Tan, Yihua Huang, Shihong Xia, Yu-Kun Lai
The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales.
no code implementations • 19 Oct 2020 • Xu sun, Zhenfeng Fan, Zihao Zhang, Yingjie Guo, Shihong Xia
The proposed framework achieves at least 40% improvement on stability evaluation metrics while enhancing detection accuracy versus state-of-the-art methods.
1 code implementation • 1 Jun 2020 • Shu-Yu Chen, Wanchao Su, Lin Gao, Shihong Xia, Hongbo Fu
Our method essentially uses input sketches as soft constraints and is thus able to produce high-quality face images even from rough and/or incomplete sketches.
1 code implementation • IEEE Transactions on Visualization and Computer Graphics ( Early Access ) 2019 • Zhiyong Wang, Jinxiang Chai, Shihong Xia
A comparison against Wang et al.[3] shows that our method advances the state of the art in 3D eye tracking using a single RGB camera.
no code implementations • 4 Oct 2018 • Yi-Ling Qiao, Lin Gao, Yu-Kun Lai, Shihong Xia
In this paper, we present a novel method for learning to synthesize 3D mesh animation sequences with long short-term memory (LSTM) blocks and mesh-based convolutional neural networks (CNNs).
Graphics
no code implementations • CVPR 2018 • Qingyang Tan, Lin Gao, Yu-Kun Lai, Shihong Xia
3D geometric contents are becoming increasingly popular.
Graphics
no code implementations • 13 Sep 2017 • Qingyang Tan, Lin Gao, Yu-Kun Lai, Jie Yang, Shihong Xia
Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing.
Graphics
no code implementations • 5 Sep 2017 • Lin Gao, Yu-Kun Lai, Jie Yang, Ling-Xiao Zhang, Leif Kobbelt, Shihong Xia
This along with a suitably chosen deformation basis including spatially localized deformation modes leads to significant advantages, including more meaningful, reliable, and efficient deformations because fewer and localized deformation modes are applied.
Graphics