当前位置: X-MOL 学术IEEE Trans. Pattern Anal. Mach. Intell. › 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.)
3D Reconstruction of “In-the-Wild” Faces in Images and Videos
IEEE Transactions on Pattern Analysis and Machine Intelligence ( IF 23.6 ) Pub Date : 2018-05-15 , DOI: 10.1109/tpami.2018.2832138
James Booth , Anastasios Roussos , Evangelos Ververas , Epameinondas Antonakos , Stylianos Ploumpis , Yannis Panagakis , Stefanos Zafeiriou

3D Morphable Models (3DMMs) are powerful statistical models of 3D facial shape and texture, and are among the state-of-the-art methods for reconstructing facial shape from single images. With the advent of new 3D sensors, many 3D facial datasets have been collected containing both neutral as well as expressive faces. However, all datasets are captured under controlled conditions. Thus, even though powerful 3D facial shape models can be learnt from such data, it is difficult to build statistical texture models that are sufficient to reconstruct faces captured in unconstrained conditions (“in-the-wild”). In this paper, we propose the first “in-the-wild” 3DMM by combining a statistical model of facial identity and expression shape with an “in-the-wild” texture model. We show that such an approach allows for the development of a greatly simplified fitting procedure for images and videos, as there is no need to optimise with regards to the illumination parameters. We have collected three new benchmarks that combine “in-the-wild” images and video with ground truth 3D facial geometry, the first of their kind, and report extensive quantitative evaluations using them that demonstrate our method is state-of-the-art.

中文翻译:

图像和视频中“狂野”面孔的3D重建

3D变形模型(3DMM)是3D面部形状和纹理的强大统计模型,并且是从单个图像重建面部形状的最新方法之一。随着新的3D传感器的出现,已经收集了许多3D面部数据集,其中既包含中性面孔,也包含富有表情的面孔。但是,所有数据集都是在受控条件下捕获的。因此,即使可以从此类数据中学习强大的3D面部形状模型,也难以构建足以重建在不受约束的条件下(“野外”)捕获的面部的统计纹理模型。在本文中,我们通过将面部识别和表情形状的统计模型与“狂野”纹理模型相结合,提出了第一个“狂野” 3DMM。我们表明,由于不需要针对照明参数进行优化,因此这种方法可以极大简化图像和视频的拟合过程。我们已经收集了三个新的基准,它们将“野生”图像和视频与地面真实3D面部几何形状相结合,这是第一个基准,并报告了使用它们进行的大量定量评估,这些数据证明了我们的方法是最新的。
更新日期:2018-10-03
down
wechat
bug