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

被引:2
|
作者
Xing, Yifan [1 ]
Tewari, Rahul [1 ]
Mendonc, Paulo R. S. [1 ]
机构
[1] Amazon Web Serv, Seattle, WA 98109 USA
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
  • [1] Self-supervised single-image 3D face reconstruction method based on attention mechanism and attribute refinement
    Qin, Xujia
    Li, Xinyu
    Li, Mengjia
    Zheng, Hongbo
    Xu, Xiaogang
    [J]. VISUAL COMPUTER, 2024,
  • [2] Enhancing Face Recognition with Self-Supervised 3D Reconstruction
    He, Mingjie
    Zhang, Jie
    Shan, Shiguang
    Chen, Xilin
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 4052 - 4061
  • [3] Self-Supervised Learning of Detailed 3D Face Reconstruction
    Chen, Yajing
    Wu, Fanzi
    Wang, Zeyu
    Song, Yibing
    Ling, Yonggen
    Bao, Linchao
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 : 8696 - 8705
  • [4] Review of Single-Image 3D Face Reconstruction Methods
    Wang, Jingting
    Li, Huibin
    [J]. Computer Engineering and Applications, 2023, 59 (17) : 1 - 21
  • [5] Self-Supervised 3D Face Reconstruction via Conditional Estimation
    Wen, Yandong
    Liu, Weiyang
    Raj, Bhiksha
    Singh, Rita
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 13269 - 13278
  • [6] From Local to Holistic: Self-supervised Single Image 3D Face Reconstruction Via Multi-level Constraints
    Lu, Yawen
    Sarkis, Michel
    Bi, Ning
    Lu, Guoyu
    [J]. 2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 8368 - 8375
  • [7] Self-Supervised 3D Mesh Reconstruction from Single Images
    Hu, Tao
    Wang, Liwei
    Xu, Xiaogang
    Liu, Shu
    Jia, Jiaya
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 5998 - 6007
  • [8] Self-supervised Single-Image Deconvolution with Siamese Neural Networks
    Papkov, Mikhail
    Palo, Kaupo
    Parts, Leopold
    [J]. DATA AUGMENTATION, LABELLING, AND IMPERFECTIONS, DALI 2023, 2024, 14379 : 157 - 166
  • [9] Multi-view self-supervised learning for 3D facial texture reconstruction from single image
    Zeng, Xiaoxing
    Hu, Ruyun
    Shi, Wu
    Qiao, Yu
    [J]. IMAGE AND VISION COMPUTING, 2021, 115
  • [10] Self-Supervised 3D Face Reconstruction Based on Multi-view UV Fusion
    Zeng, Cheng
    Li, Xiaohan
    Zhou, Xiang
    [J]. THIRTEENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2021), 2021, 11878