Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans

被引:10
|
作者
Chaudhuri, Bindita [1 ]
Sarafianos, Nikolaos [2 ]
Shapiro, Linda [1 ]
Tung, Tony [2 ]
机构
[1] Univ Washington, Seattle, WA 98195 USA
[2] Sausalito, Facebook Real Labs Res, Sausalito, CA USA
关键词
D O I
10.1109/CVPR46437.2021.00790
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We introduce a novel approach to generate diverse high fidelity texture maps for 3D human meshes in a semi-supervised setup. Given a segmentation mask defining the layout of the semantic regions in the texture map, our network generates high-resolution textures with a variety of styles, that are then used for rendering purposes. To accomplish this task, we propose a Region-adaptive Adversarial Variational AutoEncoder (ReAVAE) that learns the probability distribution of the style of each region individually so that the style of the generated texture can be controlled by sampling from the region-specific distributions. In addition, we introduce a data generation technique to augment our training set with data lifted from single-view RGB inputs. Our training strategy allows the mixing of reference image styles with arbitrary styles for different regions, a property which can be valuable for virtual try-on AR/VR applications. Experimental results show that our method synthesizes better texture maps compared to prior work while enabling independent layout and style controllability.
引用
收藏
页码:7987 / 7996
页数:10
相关论文
共 50 条
  • [41] A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection
    Wang, Hanshi
    Zhang, Zhipeng
    Gao, Jin
    Hu, Weiming
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2024, : 14978 - 14987
  • [42] Semi-supervised Segmentation of 3D Surfaces Using a Weighted Graph Representation
    Bergamasco, Filippo
    Albarelli, Andrea
    Torsello, Andrea
    GRAPH-BASED REPRESENTATIONS IN PATTERN RECOGNITION, 2011, 6658 : 225 - 234
  • [43] Semi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation
    Kaviani, Samira
    Rahimi, Amir
    Hartley, Richard
    2021 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA 2021), 2021, : 1 - 8
  • [44] Semi-supervised 3D shape segmentation with multilevel consistency and part substitution
    Chun-Yu Sun
    Yu-Qi Yang
    Hao-Xiang Guo
    Peng-Shuai Wang
    Xin Tong
    Yang Liu
    Heung-Yeung Shum
    Computational Visual Media, 2023, 9 : 229 - 247
  • [45] A graph-based technique for semi-supervised segmentation of 3D surfaces
    Bergamasco, Filippo
    Albarelli, Andrea
    Torsello, Andrea
    PATTERN RECOGNITION LETTERS, 2012, 33 (15) : 2057 - 2064
  • [46] Semi-supervised deep learning based 3D analysis of the peripapillary region
    Heisler, Morgan
    Bhalla, Mahadev
    Lo, Julian
    Mammo, Zaid
    Lee, Sieun
    Ju, Myeong Jin
    Beg, Mirza Faisal
    Sarunic, Marinko, V
    BIOMEDICAL OPTICS EXPRESS, 2020, 11 (07): : 3843 - 3856
  • [47] Method of semi-supervised distance metric learning for 3D model retrieval
    Wang, Xinying
    Wang, Shengsheng
    Lv, Tianyang
    Wang, Zhengxuan
    Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument, 2010, 31 (06): : 1399 - 1404
  • [48] A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection
    Zhang, Dingyuan
    Liang, Dingkang
    Zou, Zhikang
    Li, Jingyu
    Ye, Xiaoqing
    Liu, Zhe
    Tan, Xiao
    Bai, Xiang
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 8339 - 8349
  • [49] 3D measures exploitation for a monocular semi-supervised fall detection system
    Konstantinos Makantasis
    Eftychios Protopapadakis
    Anastasios Doulamis
    Nikolaos Doulamis
    Nikolaos Matsatsinis
    Multimedia Tools and Applications, 2016, 75 : 15017 - 15049
  • [50] Monocular 3D Detection With Geometric Constraint Embedding and Semi-Supervised Training
    Li, Peixuan
    Zhao, Huaici
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (03): : 5565 - 5572