Learning to Detect 3D Facial Landmarks via Heatmap Regression with Graph Convolutional Networks | |
Yuan Wang1,4; Min Cao2; Zhenfeng Fan3,4; Silong Peng1,4 | |
2022-06 | |
会议名称 | AAAI Conference on Artificial Intelligence |
会议日期 | 2022.2.24 |
会议地点 | 加拿大温哥华 |
会议录编者/会议主办者 | AAAI Conference on Artificial Intelligence |
摘要 | 3D facial landmark detection is extensively used in many research fields such as face registration, facial shape analysis, and face recognition. Most existing methods involve traditional features and 3D face models for the detection of landmarks, and their performances are limited by the hand-crafted intermediate process. In this paper, we propose a novel 3D facial landmark detection method, which directly locates the coordinates of landmarks from 3D point cloud with a wellcustomized graph convolutional network. The graph convolutional network learns geometric features adaptively for 3D facial landmark detection with the assistance of constructed 3D heatmaps, which are Gaussian functions of distances to each landmark on a 3D face. On this basis, we further develop a local surface unfolding and registration module to predict 3D landmarks from the heatmaps. The proposed method forms the first baseline of deep point cloud learning method for 3D facial landmark detection. We demonstrate experimentally that the proposed method exceeds the existing approaches by a clear margin on BU-3DFE and FRGC datasets for landmark localization accuracy and stability, and also achieves high precision results on a recent large-scale dataset. |
关键词 | 三维人脸关键点检测 图卷积神经网络 热力图回归 |
学科门类 | 工学 ; 工学::计算机科学与技术(可授工学、理学学位) |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 三维视觉 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51723 |
专题 | 智能制造技术与系统研究中心_多维数据分析(彭思龙)-技术团队 |
通讯作者 | Zhenfeng Fan |
作者单位 | 1.中国科学院自动化研究所, 中国科学院大学 2.苏州大学 3.中国科学院计算技术研究所 4.中国科学院大学 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yuan Wang,Min Cao,Zhenfeng Fan,et al. Learning to Detect 3D Facial Landmarks via Heatmap Regression with Graph Convolutional Networks[C]//AAAI Conference on Artificial Intelligence,2022. |
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 | ||
Learning to Detect 3(2516KB) | 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