CLOTH3D: Clothed 3D Humans

被引：93

作者：

Bertiche, Hugo ^{[1
,2
]}

Madadi, Meysam ^{[1
,2
]}

Escalera, Sergio ^{[1
,2
]}

机构：

[1] Univ Barcelona, Barcelona, Spain

[2] Comp Vis Ctr, Barcelona, Spain

来源：

COMPUTER VISION - ECCV 2020, PT XX | 2020年 / 12365卷

关键词：

3D; Human; Garment; Cloth; Dataset; Generative model;

D O I：

10.1007/978-3-030-58565-5_21

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 CLOTH3D, the first big scale synthetic dataset of 3D clothed human sequences. CLOTH3D contains a large variability on garment type, topology, shape, size, tightness and fabric. Clothes are simulated on top of thousands of different pose sequences and body shapes, generating realistic cloth dynamics. We provide the dataset with a generative model for cloth generation. We propose a Conditional Variational Auto-Encoder (CVAE) based on graph convolutions (GCVAE) to learn garment latent spaces. This allows for realistic generation of 3D garments on top of SMPL model for any pose and shape.

引用

页码：344 / 359

页数：16

共 34 条

[1] Tex2Shape: Detailed Full Human Body Geometry From a Single Image [J].

Alldieck, Thiemo ;

Pons-Moll, Gerard ;

Theobalt, Christian ;

Magnor, Marcus .

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :2293-2303

[2] Detailed Human Avatars from Monocular Video [J].

Alldieck, Thiemo ;

Magnor, Marcus ;

Xu, Weipeng ;

Theobalt, Christian ;

Pons-Moll, Gerard .

2018 INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2018, :98-109

[3]

Amberg B, 2007, IEEE I CONF COMP VIS, P1326

[4] Multi-Garment Net: Learning to Dress 3D People from Images [J].

Bhatnagar, Bharat Lal ;

Tiwari, Garvita ;

Theobalt, Christian ;

Pons-Moll, Gerard .

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :5419-5429

[5] Geometric Deep Learning Going beyond Euclidean data [J].

Bronstein, Michael M. ;

Bruna, Joan ;

LeCun, Yann ;

Szlam, Arthur ;

Vandergheynst, Pierre .

IEEE SIGNAL PROCESSING MAGAZINE, 2017, 34 (04) :18-42

[6]

Defferrard M, 2016, ADV NEUR IN, V29

[7] Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes [J].

Dong, Qi ;

Gong, Shaogang ;

Zhu, Xiatian .

2017 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2017), 2017, :520-529

[8]

Garland M., 1997, Computer Graphics Proceedings, SIGGRAPH 97, P209, DOI 10.1145/258734.258849

[9] DRAPE: DRessing Any PErson [J].

Guan, Peng ;

Reiss, Loretta ;

Hirshberg, David A. ;

Weiss, Alexander ;

Black, Michael J. .

ACM TRANSACTIONS ON GRAPHICS, 2012, 31 (04)

[10] GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping [J].

Gundogdu, Erhan ;

Constantin, Victor ;

Seifoddini, Amrollah ;

Dang, Minh ;

Salzmann, Mathieu ;

Fua, Pascal .

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :8738-8747

← 1 2 3 4 →