A Self-Supervised Bootstrap Method for Single-Image 3D Face Reconstruction

被引:3
|
作者
Xing, Yifan [1 ]
Tewari, Rahul [1 ]
Mendonc, Paulo R. S. [1 ]
机构
[1] Amazon Web Serv, Seattle, WA 98109 USA
来源
2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) | 2019年
关键词
DATABASE;
D O I
10.1109/WACV.2019.00113
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
State-of-the-art methods for 3D reconstruction of faces from a single image require 2D-3D pairs of ground-truth data for supervision. Such data is costly to acquire, and most datasets available in the literature are restricted to pairs for which the input 2D images depict faces in a near fronto-parallel pose. Therefore, many data-driven methods for single-image 3D facial reconstruction perform poorly on profile and near-profile faces. We propose a method to improve the performance of single-image 3D facial reconstruction networks by utilizing the network to synthesize its own training data for fine-tuning, comprising: (i) single-image 3D reconstruction of faces in near-frontal images without ground-truth 3D shape; (ii) application of a rigid-body transformation to the reconstructed face model; (iii) rendering of the face model from new viewpoints; and (iv) use of the rendered image and corresponding 3D reconstruction as additional data for supervised fine-tuning. The new 2D-3D pairs thus produced have the same high-quality observed for near fronto-parallel reconstructions, thereby nudging the network towards more uniform performance as a function of the viewing angle of input faces. Application of the proposed technique to the fine-tuning of a state-of-the-art single-image 3D-reconstruction network for faces demonstrates the usefulness of the method, with particularly significant gains for profile or near-profile views.
引用
收藏
页码:1014 / 1023
页数:10
相关论文
共 50 条
  • [11] Self-supervised learning for fine-grained monocular 3D face reconstruction in the wild
    Huang, Dongjin
    Shi, Yongsheng
    Liu, Jinhua
    Tang, Wen
    MULTIMEDIA SYSTEMS, 2024, 30 (04)
  • [12] Self-Supervised 3D Face Reconstruction Based on Multi-view UV Fusion
    Zeng, Cheng
    Li, Xiaohan
    Zhou, Xiang
    THIRTEENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2021), 2021, 11878
  • [13] Single-image reflection removal via self-supervised diffusion models
    Lu, Zhengyang
    Wang, Weifan
    Guo, Tianhao
    Wang, Feng
    JOURNAL OF SUPERCOMPUTING, 2025, 81 (01):
  • [14] Self-supervised Super-plane for Neural 3D Reconstruction
    Ye, Botao
    Liu, Sifei
    Li, Xueting
    Yang, Ming-Hsuan
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 21415 - 21424
  • [15] Self-Supervised Single-Image Depth Estimation From Focus and Defocus Clues
    Lu, Yawen
    Milliron, Garrett
    Slagter, John
    Lu, Guoyu
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (04) : 6281 - 6288
  • [16] RepC-MVSNet: A Reparameterized Self-Supervised 3D Reconstruction Algorithm for Wheat 3D Reconstruction
    Liu, Hui
    Xin, Cheng
    Lai, Mengzhen
    He, Hangfei
    Wang, Yongzhao
    Wang, Mantao
    Li, Jun
    AGRONOMY-BASEL, 2023, 13 (08):
  • [17] Topology-Aware Single-Image 3D Shape Reconstruction
    Chen, Qimin
    Nguyen, Vincent
    Han, Feng
    Kiveris, Raimondas
    Tu, Zhuowen
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, : 1089 - 1097
  • [18] Self-supervised neural network-based endoscopic monocular 3D reconstruction method
    Zhang, Ziming
    Tan, Wenjun
    Sun, Yuhang
    Han, Juntao
    Wang, Zhe
    Xue, Hongsheng
    Wang, Ruoyu
    HEALTH INFORMATION SCIENCE AND SYSTEMS, 2023, 12 (01)
  • [19] Self-supervised Image-based 3D Model Retrieval
    Song, Dan
    Zhang, Chu-Meng
    Zhao, Xiao-Qian
    Wang, Teng
    Nie, Wei-Zhi
    Li, Xuan-Ya
    Liu, An-An
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2023, 19 (02)
  • [20] Video supervised for 3D reconstruction from single image
    Zhong, Yijie
    Sun, Zhengxing
    Luo, Shoutong
    Sun, Yunhan
    Wang, Yi
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (11) : 15061 - 15083