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
  • [31] Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose
    Wang, Angtian
    Mei, Shenxiao
    Yuille, Alan
    Kortylewski, Adam
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [32] Self-supervised learning for accelerated 3D high-resolution ultrasound imaging
    Dai, Xianjin
    Lei, Yang
    Wang, Tonghe
    Axente, Marian
    Xu, Dong
    Patel, Pretesh
    Jani, Ashesh B.
    Curran, Walter J.
    Liu, Tian
    Yang, Xiaofeng
    MEDICAL PHYSICS, 2021, 48 (07) : 3916 - 3926
  • [33] 3D measures exploitation for a monocular semi-supervised fall detection system
    Makantasis, Konstantinos
    Protopapadakis, Eftychios
    Doulamis, Anastasios
    Doulamis, Nikolaos
    Matsatsinis, Nikolaos
    MULTIMEDIA TOOLS AND APPLICATIONS, 2016, 75 (22) : 15017 - 15049
  • [34] Dual consistency semi-supervised learning for 3D medical image segmentation
    Wei, Lin
    Sha, Runxuan
    Shi, Yucheng
    Wang, Qingxian
    Shi, Lei
    Gao, Yufei
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2025, 104
  • [35] 3D model Autotagging Based on Semi-supervised Weighted Metric Learning
    Kai, Zhou
    Feng, Tian
    Zhong, Ren
    Guo, Hao
    2014 PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE & EDUCATION (ICCSE 2014), 2014, : 785 - 788
  • [36] Class-Level Confidence Based 3D Semi-Supervised Learning
    Chen, Zhimin
    Jing, Longlong
    Yang, Liang
    Li, Yingwei
    Li, Bing
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 633 - 642
  • [37] Semi-supervised 3D shape segmentation with multilevel consistency and part substitution
    Sun, Chun-Yu
    Yang, Yu-Qi
    Guo, Hao-Xiang
    Wang, Peng-Shuai
    Tong, Xin
    Liu, Yang
    Shum, Heung-Yeung
    COMPUTATIONAL VISUAL MEDIA, 2023, 9 (02) : 229 - 247
  • [38] Semi-supervised Clustering with Associative-Link Constraints for 3D Models
    Zhang, Shaohong
    Wang, Jing
    Wu, Xiaoqiang
    Zeng, Baoying
    Qiu, Wenxiao
    Xie, Dongqing
    2015 12TH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (FSKD), 2015, : 1665 - 1669
  • [39] Semi-Supervised Learning in Reconstructed Manifold Space for 3D Caricature Generation
    Liu, Junfa
    Chen, Yiqiang
    Miao, Chunyan
    Xie, Jinjing
    Ling, Charles X.
    Gao, Xingyu
    Gao, Wen
    COMPUTER GRAPHICS FORUM, 2009, 28 (08) : 2104 - 2116
  • [40] A Semi-supervised Data Augmentation Approach Using 3D Graphical Engines
    Liu, Shuangjun
    Ostadabbas, Sarah
    COMPUTER VISION - ECCV 2018 WORKSHOPS, PT II, 2019, 11130 : 395 - 408