Disentangled Representation Transformer Network for 3D Face Reconstruction and Robust Dense Alignment

分类： 计算机科学 >> 计算机科学技术其他学科 提交时间： 2023-03-02

Xiangzheng Li Xiaofei Li Jia Deng

摘要： In this paper, we propose a disentangled representation transformer network (DRTN) approach for 3D dense face alignment and reconstruction.Unlike traditional 3DMM-based approaches in which the target parameters, namely the shape, expression, and pose parameters, are all individually estimated, without considering their direct influences on one another, although they are jointly optimized our DRTN aims to enhance the representation of facial attributes in a semantic sense by learning the correlation of different 3D facial attribute parameters.To achieve this we present a novel strategy to design disentangled 3D face attribute representation,which decomposes the given facial attributes into identity, expression, and poses parts. Specifically, the estimate of 3D face parameters in the regression network depends on the correlation of other face attribute parameters rather than being independent. The branching of the identity component aims to reinforce the learning of expression and pose attributes by preserving the overall face geometry structure and keeping the identity intact. Accordingly, the expression and pose parts of the branch maintain the consistency of expression and pose attributes, respectively. It helps refine the reconstruction and alignment of face details in large poses mainly by coupling other facial attribute parameters. Extensive qualitative and quantitative experimental results on widely-evaluated benchmarking datasets demonstrate that our approach achieves competitive performance compared to state-of-the-art methods.

同行评议状态:待评议

 点击量 2629  下载量 286  评论