Learning-by-Novel-View-Synthesis for Full-Face Appearance-Based 3D Gaze Estimation

被引:0
|
作者
Qin, Jiawei [1 ]
Shimoyama, Takuru [1 ]
Sugano, Yusuke [1 ]
机构
[1] Univ Tokyo, Inst Ind Sci, Tokyo, Japan
关键词
CONSENSUS; TRACKING;
D O I
10.1109/CVPRW56347.2022.00546
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Despite recent advances in appearance-based gaze estimation techniques, the need for training data that covers the target head pose and gaze distribution remains a crucial challenge for practical deployment. This work examines a novel approach for synthesizing gaze estimation training data based on monocular 3D face reconstruction. Unlike prior works using multi-view reconstruction, photo-realistic CG models, or generative neural networks, our approach can manipulate and extend the head pose range of existing training data without any additional requirements. We introduce a projective matching procedure to align the reconstructed 3D facial mesh with the camera coordinate system and synthesize face images with accurate gaze labels. We also propose a mask-guided gaze estimation model and data augmentation strategies to further improve the estimation accuracy by taking advantage of synthetic training data. Experiments using multiple public datasets show that our approach significantly improves the estimation performance on challenging cross-dataset settings with non-overlapping gaze distributions.
引用
收藏
页码:4977 / 4987
页数:11
相关论文
共 50 条
  • [1] Learning-by-Synthesis for Appearance-based 3D Gaze Estimation
    Sugano, Yusuke
    Matsushita, Yasuyuki
    Sato, Yoichi
    [J]. 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 1821 - 1828
  • [2] It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation
    Zhang, Xucong
    Sugano, Yusuke
    Fritz, Mario
    Bulling, Andreas
    [J]. 2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, : 2299 - 2308
  • [3] Federated Learning for Appearance-based Gaze Estimation in the Wild
    Elfares, Mayar
    Hu, Zhiming
    Reisert, Pascal
    Bulling, Andreas
    Kuesters, Ralf
    [J]. GAZE MEETS MACHINE LEARNING WORKSHOP, VOL 210, 2022, 210 : 20 - 36
  • [4] Appearance-Based Gaze Estimation With Deep Learning: A Review and Benchmark
    Cheng, Yihua
    Wang, Haofei
    Bao, Yiwei
    Lu, Feng
    [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46 (12) : 7509 - 7528
  • [5] Appearance-based Color Face Recognition With 3D Model
    Wang, Chengzhang
    Bai, Xiaoming
    [J]. INTERNATIONAL CONFERENCE ON GRAPHIC AND IMAGE PROCESSING (ICGIP 2012), 2013, 8768
  • [6] Evaluation of an appearance-based 3D face tracker using dense 3D data
    Fadi Dornaika
    Angel D. Sappa
    [J]. Machine Vision and Applications, 2008, 19 : 427 - 441
  • [7] Evaluation of an appearance-based 3D face tracker using dense 3D data
    Dornaika, Fadi
    Sappa, Angel D.
    [J]. MACHINE VISION AND APPLICATIONS, 2008, 19 (5-6) : 427 - 441
  • [8] Improving appearance-based 3D face tracking using sparse stereo data
    Dornaika, Fadi
    Sappa, Angel D.
    [J]. VISAPP 2006: PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 2, 2006, : 310 - +
  • [9] Improving appearance-based 3D face tracking using sparse stereo data
    Dornaika, Fadi
    Sappa, Angel D.
    [J]. ADVANCES IN COMPUTER GRAPHICS AND COMPUTER VISION, 2007, 4 : 354 - 366
  • [10] VIEW-BASED APPEARANCE MODEL ONLINE LEARNING FOR 3D DEFORMABLE FACE TRACKING
    Lefevre, Stephanie
    Odobez, Jean-Marc
    [J]. VISAPP 2010: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 1, 2010, : 223 - 230