imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose

被引:42
作者
Alldieck, Thiemo [1 ]
Xu, Hongyi [1 ]
Sminchisescu, Cristian [1 ]
机构
[1] Google Res, Mountain View, CA 94043 USA
来源
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) | 2021年
关键词
D O I
10.1109/ICCV48922.2021.00541
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present imGHUM, the first holistic generative model of 3D human shape and articulated pose, represented as a signed distance function. In contrast to prior work, we model the full human body implicitly as a function zero-level-set and without the use of an explicit template mesh. We propose a novel network architecture and a learning paradigm, which make it possible to learn a detailed implicit generative model of human pose, shape, and semantics, on par with state-of-the-art mesh-based models. Our model features desired detail for human models, such as articulated pose including hand motion and facial expressions, a broad spectrum of shape variations, and can be queried at arbitrary resolutions and spatial locations. Additionally, our model has attached spatial semantics making it straightforward to establish correspondences between different shape instances, thus enabling applications that are difficult to tackle using classical implicit representations. In extensive experiments, we demonstrate the model accuracy and its applicability to current research problems.
引用
收藏
页码:5441 / 5450
页数:10
相关论文
共 52 条
[1]   Learning to Reconstruct People in Clothing from a Single RGB Camera [J].
Alldieck, Thiemo ;
Magnor, Marcus ;
Bhatnagar, Bharat Lal ;
Theobalt, Christian ;
Pons-Moll, Gerard .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :1175-1186
[2]   SAL: Sign Agnostic Learning of Shapes from Raw Data [J].
Atzmon, Matan ;
Lipman, Yaron .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :2562-2571
[3]  
Bhatnagar BL, 2020, ADV NEUR IN, V33
[4]  
Bogo Federica, 2014, IEEE C COMP VIS PATT
[5]   Learning Implicit Fields for Generative Shape Modeling [J].
Chen, Zhiqin ;
Zhang, Hao .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :5932-5941
[6]   Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion [J].
Chibane, Julian ;
Alldieck, Thiemo ;
Pons-Moll, Gerard .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :6968-6979
[7]  
Chibane J, 2020, ADV NEUR IN, V33
[8]  
Chibane Julian, 2020, EUR C COMP VIS WORKS
[9]  
Deng Boyang, 2020, EUR C COMP VIS, V2, P7
[10]   Local Deep Implicit Functions for 3D Shape [J].
Genova, Kyle ;
Cole, Forrester ;
Sud, Avneesh ;
Sarna, Aaron ;
Funkhouser, Thomas .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :4856-4865