计算机科学
人工智能
计算机视觉
单眼
面子(社会学概念)
边距(机器学习)
变压器
模式识别(心理学)
机器学习
社会科学
量子力学
物理
社会学
电压
作者
Tianke Zhang,Xuangeng Chu,Yunfei Liu,Lijian Lin,Zhendong Yang,Zhengzhuo Xu,Chengkun Cao,Fei Richard Yu,Changyin Zhou,Chun Yuan,Yu Li
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2023-10-01
卷期号:: 8999-9008
被引量:52
标识
DOI:10.1109/iccv51070.2023.00829
摘要
Accurately reconstructing 3D faces from monocular images and videos is crucial for various applications, such as digital avatar creation. However, the current deep learning-based methods face significant challenges in achieving accurate reconstruction with disentangled facial parameters and ensuring temporal stability in single-frame methods for 3D face tracking on video data. In this paper, we propose TokenFace, a transformer-based monocular 3D face reconstruction model. TokenFace uses separate tokens for different facial components to capture information about different facial parameters and employs temporal transformers to capture temporal information from video data. This design can naturally disentangle different facial components and is flexible to both 2D and 3D training data. Trained on hybrid 2D and 3D data, our model shows its power in accurately reconstructing faces from images and producing stable results for video data. Experimental results on popular benchmarks NoWand Stirling demonstrate that TokenFace achieves state-of-the-art performance, outperforming existing methods on all metrics by a large margin.
科研通智能强力驱动
Strongly Powered by AbleSci AI