当前位置: X-MOL 学术Int. J. Comput. Vis. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Large Scale 3D Morphable Models
International Journal of Computer Vision ( IF 19.5 ) Pub Date : 2017-04-08 , DOI: 10.1007/s11263-017-1009-7
James Booth 1 , Anastasios Roussos 1, 2 , Allan Ponniah 3 , David Dunaway 3 , Stefanos Zafeiriou 1
Affiliation  

We present large scale facial model (LSFM)—a 3D Morphable Model (3DMM) automatically constructed from 9663 distinct facial identities. To the best of our knowledge LSFM is the largest-scale Morphable Model ever constructed, containing statistical information from a huge variety of the human population. To build such a large model we introduce a novel fully automated and robust Morphable Model construction pipeline, informed by an evaluation of state-of-the-art dense correspondence techniques. The dataset that LSFM is trained on includes rich demographic information about each subject, allowing for the construction of not only a global 3DMM model but also models tailored for specific age, gender or ethnicity groups. We utilize the proposed model to perform age classification from 3D shape alone and to reconstruct noisy out-of-sample data in the low-dimensional model space. Furthermore, we perform a systematic analysis of the constructed 3DMM models that showcases their quality and descriptive power. The presented extensive qualitative and quantitative evaluations reveal that the proposed 3DMM achieves state-of-the-art results, outperforming existing models by a large margin. Finally, for the benefit of the research community, we make publicly available the source code of the proposed automatic 3DMM construction pipeline, as well as the constructed global 3DMM and a variety of bespoke models tailored by age, gender and ethnicity.

中文翻译:

大型 3D 可变形模型

我们展示了大规模面部模型 (LSFM)——一种 3D 可变形模型 (3DMM),由 9663 个不同的面部身份自动构建。据我们所知,LSFM 是有史以来构建的规模最大的 Morphable 模型,包含来自各种人群的统计信息。为了构建如此大的模型,我们引入了一种新颖的全自动且强大的 Morphable Model 构建管道,通过对最先进的密集对应技术的评估提供信息。LSFM 训练的数据集包括关于每个主题的丰富人口统计信息,不仅可以构建全局 3DMM 模型,还可以构建针对特定年龄、性别或种族群体的模型。我们利用所提出的模型仅从 3D 形状执行年龄分类,并在低维模型空间中重建噪声样本外数据。此外,我们对构建的 3DMM 模型进行系统分析,以展示其质量和描述能力。所提出的广泛的定性和定量评估表明,所提出的 3DMM 实现了最先进的结果,大大优于现有模型。最后,为了研究界的利益,我们公开了提议的自动 3DMM 构建管道的源代码,以及构建的全局 3DMM 和各种按年龄、性别和种族定制的定制模型。我们对构建的 3DMM 模型进行系统分析,以展示其质量和描述能力。所提出的广泛的定性和定量评估表明,所提出的 3DMM 实现了最先进的结果,大大优于现有模型。最后,为了研究界的利益,我们公开了提议的自动 3DMM 构建管道的源代码,以及构建的全局 3DMM 和各种按年龄、性别和种族定制的定制模型。我们对构建的 3DMM 模型进行系统分析,以展示其质量和描述能力。所提出的广泛的定性和定量评估表明,所提出的 3DMM 实现了最先进的结果,大大优于现有模型。最后,为了研究界的利益,我们公开了提议的自动 3DMM 构建管道的源代码,以及构建的全局 3DMM 和各种按年龄、性别和种族定制的定制模型。
更新日期:2017-04-08
down
wechat
bug