Geometry Sampling-Based Adaption to DCGAN for 3D Face Generation

Author:

Luo Guoliang1,Xiong Guoming1,Huang Xiaojun1,Zhao Xin1,Tong Yang1,Chen Qiang1,Zhu Zhiliang1ORCID,Lei Haopeng2,Lin Juncong3

Affiliation:

1. Virtual Reality and Interactive Techniques Institute, East China Jiaotong University, Nanchang 330013, China

2. School of Computer Science, Jiangxi Normal University, Nanchang 330022, China

3. School of Information, Xiamen University, Xiamen 361005, China

Abstract

Despite progress in the past decades, 3D shape acquisition techniques are still a threshold for various 3D face-based applications and have therefore attracted extensive research. Moreover, advanced 2D data generation models based on deep networks may not be directly applicable to 3D objects because of the different dimensionality of 2D and 3D data. In this work, we propose two novel sampling methods to represent 3D faces as matrix-like structured data that can better fit deep networks, namely (1) a geometric sampling method for the structured representation of 3D faces based on the intersection of iso-geodesic curves and radial curves, and (2) a depth-like map sampling method using the average depth of grid cells on the front surface. The above sampling methods can bridge the gap between unstructured 3D face models and powerful deep networks for an unsupervised generative 3D face model. In particular, the above approaches can obtain the structured representation of 3D faces, which enables us to adapt the 3D faces to the Deep Convolution Generative Adversarial Network (DCGAN) for 3D face generation to obtain better 3D faces with different expressions. We demonstrated the effectiveness of our generative model by producing a large variety of 3D faces with different expressions using the two novel down-sampling methods mentioned above.

Funder

Natural Science Foundation of Guangdong Province

Ministry of Science and Technology of China

Key Research and Development Program of Jiangxi Province

National Natural Science Foundation of China

Natural Science Foundation of Jiangxi Province

Publisher

MDPI AG

Subject

Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry

Reference44 articles.

1. Richardson, E., Sela, M., and Kimmel, R. (2016, January 25–28). 3d face reconstruction by learning from synthetic data. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.

2. Gilani, S.Z., and Mian, A. (2018, January 18–23). Learning from millions of 3d scans for large-scale 3d face recognition. Proceedings of the IEEE Conference of Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.

3. Luo, G., Zhao, X., Tong, Y., Chen, Q., Zhu, Z., Lei, H., and Lin, J. (2020, January 19–24). Geometry Sampling for 3D Face Generation via DCGAN. Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.

4. Gabor convolutional networks;Luan;IEEE Trans. Image Process.,2018

5. Minaee, S., Liang, X., and Yan, S. (2022). Modern augmented reality: Applications, trends, and future directions. arXiv.

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3