Knowledge Commons of Institute of Automation,CAS
Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Network. | |
Keqiang Li1,2; Huaiyu Wu1; Xiuqin Shang3; Zhen Shen3; Gang Xiong4; Xisong Dong1; Bin Hu1; Fei-Yue Wang1 | |
2021-01 | |
会议名称 | 2020 25th International Conference on Pattern Recognition (ICPR) |
会议录名称 | ICPR |
卷号 | ICPR48806 |
期号 | 2021 |
页码 | 6973-6979 |
会议日期 | 10-15 Jan. 2021 |
会议地点 | Milan, Italy |
会议录编者/会议主办者 | IAPR |
出版地 | American |
出版者 | IEEE |
摘要 | 3D face reconstruction from a single 2D facial image is a challenging and concerned problem. Recent methods based on CNN typically aim to learn parameters of 3D Morphable Model (3DMM) from 2D images to render face alignment and 3D face reconstruction. Most algorithms are designed for faces with small, medium yaw angles, which is extremely challenging to align faces in large poses. At the same time, they are not efficient usually. The main challenge is that it takes time to determine the parameters accurately. In order to address this challenge with the goal of improving performance, this paper proposes a novel and efficient end-to-end framework. We design an efficient and lightweight network model combined with Depthwise Separable Convolution and Muti-scale Representation, Lightweight Attention Mechanism, named Mobile-FRNet. Simultaneously, different loss functions are used to constrain and optimize 3DMM parameters and 3D vertices during training to improve the performance of the network. Meanwhile, extensive experiments on the challenging datasets show that our method significantly improves the accuracy of face alignment and 3D face reconstruction. Model parameters and complexity of our method are also improved greatly. |
关键词 | face alignment, 3D face reconstruction, 3DMM |
DOI | 10.1109/ICPR48806.2021.9412196 |
URL | 查看原文 |
收录类别 | EI |
资助项目 | National Natural Science Foundation of China[61872365] |
语种 | 英语 |
七大方向——子方向分类 | 三维视觉 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/47431 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
通讯作者 | Huaiyu Wu |
作者单位 | 1.The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.The Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation, Chinese Academy of Sciences 4.The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing, Cloud Computing Center, Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Keqiang Li,Huaiyu Wu,Xiuqin Shang,et al. Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Network.[C]//IAPR. American:IEEE,2021:6973-6979. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Joint_Face_Alignment(4004KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论