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
[31]   Expressive Body Capture: 3D Hands, Face, and Body from a Single Image [J].
Pavlakos, Georgios ;
Choutas, Vasileios ;
Ghorbani, Nima ;
Bolkart, Timo ;
Osman, Ahmed A. A. ;
Tzionas, Dimitrios ;
Black, Michael J. .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :10967-10977
[32]   Building statistical shape spaces for 3D human modeling [J].
Pishchulin, Leonid ;
Wuhrer, Stefanie ;
Helten, Thomas ;
Theobalt, Christian ;
Schiele, Bernt .
PATTERN RECOGNITION, 2017, 67 :276-286
[33]  
Plänkers R, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P394, DOI 10.1109/ICCV.2001.937545
[34]   Dyna: A Model of Dynamic Human Shape in Motion [J].
Pons-Moll, Gerard ;
Romero, Javier ;
Mahmood, Naureen ;
Black, Michael J. .
ACM TRANSACTIONS ON GRAPHICS, 2015, 34 (04)
[35]  
Qi C.R., Adv. Neural Inf. Process. Syst., V30
[36]  
Rahaman N, 2019, PR MACH LEARN RES, V97
[37]  
Ramachandran P., 2017, arXiv
[38]   PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization [J].
Saito, Shunsuke ;
Huang, Zeng ;
Natsume, Ryota ;
Morishima, Shigeo ;
Kanazawa, Angjoo ;
Li, Hao .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :2304-2314
[39]  
Saito Shunsuke, 2020, IEEE C COMP VIS PATT
[40]  
Saito Shunsuke, 2021, IEEE C COMP VIS PATT