FACE MODELS: HOW GOOD DOES MY DATA NEED TO BE?

被引：0

作者：

Luo, Jiahao ^{[1
]}

Khan, Fahim ^{[1
]}

Mori, Issei ^{[1
]}

de Silva, Akila ^{[1
]}

Ruezga, Eric ^{[1
]}

Davis, James ^{[1
]}

机构：

[1] Univ Calif Santa Cruz, Santa Cruz, CA 95064 USA

来源：

2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2021年

关键词：

Imaging; 3D; Face Models;

D O I：

10.1109/ICIP42928.2021.9506668

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Face models are widely used in image processing and other domains. The input data to create a 3D face model ranges from accurate laser scans to simple 2D RGB photographs. System designers must choose a source of input data and then choose a reconstruction method to obtain a usable 3D face. If a particular application domain requires accuracy X, which kinds of input data are suitable? This paper takes a step toward answering this question. A variety of common input data types such as 2D landmarks and 3D scans are constructed from an existing high quality dataset. A morphable face model is then used to reconstruct 3D faces. By comparing to ground truth, an analysis of the relative error between different data types is obtained.

引用

页码：3188 / 3192

页数：5