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
  • [21] 3D Features for human action recognition with semi-supervised learning
    Sahoo, Suraj Prakash
    Srinivasu, Ulli
    Ari, Samit
    IET IMAGE PROCESSING, 2019, 13 (06) : 983 - 990
  • [22] Translation Consistent Semi-Supervised Segmentation for 3D Medical Images
    Liu, Yuyuan
    Tian, Yu
    Wang, Chong
    Chen, Yuanhong
    Liu, Fengbei
    Belagiannis, Vasileios
    Carneiro, Gustavo
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2025, 44 (02) : 952 - 968
  • [23] Bayesian Self-training for Semi-supervised 3D Segmentation
    Unal, Ozan
    Sakaridis, Christos
    Van Gool, Luc
    COMPUTER VISION - ECCV 2024, PT LVI, 2025, 15114 : 89 - 107
  • [24] Federated Semi-Supervised Classification of Multimedia Flows for 3D Networks
    Bano, Saira
    Machumilane, Achilles
    Valerio, Lorenzo
    Cassara, Pietro
    Gotta, Alberto
    2022 IEEE 21ST MEDITERRANEAN ELECTROTECHNICAL CONFERENCE (IEEE MELECON 2022), 2022, : 165 - 170
  • [25] Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation
    Wu, Yizheng
    Pan, Zhiyu
    Wang, Kewei
    Li, Xingyi
    Cui, Jiahao
    Xiao, Liwen
    Lin, Guosheng
    Cao, Zhiguo
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (12) : 9567 - 9582
  • [26] Learning with Noisy Data for Semi-Supervised 3D Object Detection
    Chen, Zehui
    Li, Zhenyu
    Wang, Shuo
    Fu, Dengpan
    Zhao, Feng
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 6906 - 6916
  • [27] FocalMix: Semi-Supervised Learning for 3D Medical Image Detection
    Wang, Dong
    Zhang, Yuan
    Zhang, Kexin
    Wang, Liwei
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 3950 - 3959
  • [28] Semi-supervised Metric Learning for 3D Model Automatic Annotation
    Tian, Feng
    Shen, Xu-kun
    Liu, Xian-mei
    Zhou, Kai
    ADVANCES IN MULTIMEDIA, SOFTWARE ENGINEERING AND COMPUTING, VOL 1, 2011, 128 : 85 - +
  • [29] A semi-supervised 3D object detection method for autonomous driving
    Zhang, Jiacheng
    Liu, Huafeng
    Lu, Jianfeng
    DISPLAYS, 2022, 71
  • [30] Joint Semi-Supervised and Active Learning via 3D Consistency for 3D Object Detection
    Hwang, Sihwan
    Kim, Sanmin
    Kim, Youngseok
    Kum, Dongsuk
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA, 2023, : 4819 - 4825