Multiface：一个用于神经人脸渲染的数据集
计算机视觉与模式识别
2023-06-27 v2 图形学
摘要
近年来照片级真实人脸化身已取得长足进展，但该领域研究受限于缺乏公开可用、同时涵盖密集多视角相机捕获与丰富面部表情的高质量数据集。本工作中，我们提出Multiface，一个在Reality Labs Research采集自13个身份的多视角高分辨率人脸数据集，用于神经人脸渲染。我们介绍了Mugsy，一种用于捕获面部表演高分辨率同步视频的大规模多相机装置。Multiface的目标是为学术界缩小高质量数据可及性的差距，并赋能VR临场感研究。随数据集发布，我们针对不同的模型架构对新颖视角与表情插值能力的影响进行了消融研究。以条件VAE模型为基线，我们发现加入空间偏置、纹理扭曲场与残差连接可提升新颖视角合成的性能。我们的代码与数据见：https://github.com/facebookresearch/multiface
引用
@article{arxiv.2207.11243,
title = {Multiface: A Dataset for Neural Face Rendering},
author = {Cheng-hsin Wuu and Ningyuan Zheng and Scott Ardisson and Rohan Bali and Danielle Belko and Eric Brockmeyer and Lucas Evans and Timothy Godisart and Hyowon Ha and Xuhua Huang and Alexander Hypes and Taylor Koska and Steven Krenn and Stephen Lombardi and Xiaomin Luo and Kevyn McPhail and Laura Millerschoen and Michal Perdoch and Mark Pitts and Alexander Richard and Jason Saragih and Junko Saragih and Takaaki Shiratori and Tomas Simon and Matt Stewart and Autumn Trimble and Xinshuo Weng and David Whitewolf and Chenglei Wu and Shoou-I Yu and Yaser Sheikh},
journal= {arXiv preprint arXiv:2207.11243},
year = {2023}
}