基于区域敏感生成对抗网络的自动上妆算法
作者:
作者简介:

包仁达(1994-),男,河北石家庄人,硕士,主要研究领域为生成对抗网络,图像语义分割;黄少飞(1996-),女,硕士,主要研究领域为基于生成对抗网络的人脸编辑及应用;庾涵(1992-),女,硕士,主要研究领域为图像语义分割,关键点检测;孙瑶(1983-),男,博士,副研究员,主要研究领域为密码哈希函数分析,代数方程组求解算法研究,符号计算,计算机视觉;朱德发(1994-),男,硕士,主要研究领域为图像及视频合成,迁移学习;刘偲(1985-),女,博士,副教授,CCF专业会员,主要研究领域为深度学习,计算机视觉,多媒体分析.

通讯作者:

刘偲,E-mail:liusi@buaa.edu.cn

基金项目:

国家自然科学基金(U1536203,61572493,61876177)


Automatic Makeup with Region Sensitive Generative Adversarial Networks
Author:
Fund Project:

National Natural Science Foundation of China (U1536203, 61572493, 61876177)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [46]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    自动上妆旨在通过计算机算法实现人脸妆容的编辑与合成,隶属于人脸图像分析领域.其在互动娱乐应用、图像视频编辑、辅助人脸识别等多方面起着重要作用.然而作为人脸编辑任务,其仍难以在保证图像的编辑结果自然、真实的同时又很好地满足编辑需求,并且仍有难以精确控制编辑区域、图像编辑前后一致性差、图像质量不够精细等问题.针对以上难点,创新性地提出了一种掩模控制的自动上妆生成对抗网络,该网络利用掩模方法,能够重点编辑上妆区域,约束人脸妆容编辑中无需编辑的区域不变,保持主体信息.同时其又能单独编辑人脸的眼影、嘴唇、脸颊等局部区域,实现特定区域上妆,丰富了上妆功能.此外,该网络能够进行多数据集联合训练,除妆容数据集外,还可以使用其他人脸数据集作为辅助,增强模型的泛化能力,得到更加自然的上妆结果.最后,依据多种评价标准,进行了充分的定性及定量实验,并与目前的主流算法进行了对比,综合评价了所提方法的性能.

    Abstract:

    Automatic makeup refers to the editing and synthesis of face makeup through computer algorithms. It belongs to the field of face image analysis, and plays an important role in interactive entertainment applications, image and video editing, and face recognition. However, as a face editing problem, it is still difficult to ensure that the editing result of the image is natural and satisfies the editing requirements. Makeup still has some difficulties such as precisely controlling the editing area is hard, the image consistency before and after editing is poor, and the image quality is insufficient. In response to these difficulties, this study innovatively proposes a mask-controlled automatic makeup generative adversarial network. Through a masking method, this network can edit the makeup area with emphasis, restrict the area that does not require editing, and maintain the key information. At the same time, it can separately edit the eye shadow, lips, cheeks, and other local areas of the face to achieve makeup on specific areas and enrich the makeup function. In addition, this network can be trained jointly on multiple datasets. In addition to makeup dataset, it can also use other face datasets as an aid to enhance the model's generalization ability and get a more natural makeup result. Finally, based on a variety of evaluation methods, more comprehensive qualitative and quantitative experiments are carried out, the results are compared with the other methods, and the performance of the proposed method is comprehensively evaluated.

    参考文献
    [1] Denton EL, Chintala S, Fergus R. Deep generative image models using a Laplacian pyramid of adversarial networks. In:Proc. of the Int'l Conf. on Neural Information Processing Systems. 2015. 1486-1494.
    [2] Huang X, Li Y, Poursaeed O, Hopcroft JE, Belongie SJ. Stacked generative adversarial networks. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 2:3.
    [3] Zhao J, Mathieu M, LeCun Y. Energy-based generative adversarial network. In:Proc. of the Int'l Conf. on Learning Representations. 2017. 2.
    [4] Guo D, Sim T. Digital face makeup by example. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2009. 73-79.
    [5] Scherbaum K, Ritschel T, Hullin M, Thormählen T, Blanz V, Seidel HP. Computer-suggested facial makeup. Computer Graphics Forum, 2011,30(2):485-492.
    [6] Tong WS, Tang CK, Brown MS, Xu YQ. Example-based cosmetic transfer. In:Proc. of the Computer Graphics and Applications. 2007. 211-218.
    [7] Liu L, Xing J, Liu S, Xu H, Zhou X, Yan S. Wow! you are so beautiful today! ACM Trans. on Multimedia Computing, Communications, and Applications, 2014,11(1s):20.
    [8] Isola P, Zhu JY, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 5967-5976.
    [9] Zhu JY, Park T, Isola P, Efros AA. Unpaired image-to-image translation using cycle-consistent adversarial networks. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2017. 2242-2251.
    [10] Kim T, Cha M, Kim H, Lee JK, Kim J. Learning to discover cross-domain relations with generative adversarial networks. In:Proc. of the Int'l Conf. on Machine Learning. 2017. 1857-1865.
    [11] Mirza M, Osindero S. Conditional generative adversarial nets. arXiv Preprint arXiv:1411.1784, 2014.
    [12] Resales R, Achan K, Frey B. Unsupervised image translation. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2003,1:472-478.
    [13] Zhu JY, Krähenbühl P, Shechtman E, Efros AA. Generative visual manipulation on the natural image manifold. In:Proc. of the European Conf. on Computer Vision. 2016. 597-613.
    [14] Ledig C, Theis L, Huszár F, Caballero J, Cunningham A, Acosta A, Shi W. Photo-realistic single image super-resolution using a generative adversarial network. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 105-114.
    [15] Li M, Zuo W, Zhang D. Deep identity-aware transfer of facial attributes. arXiv Preprint arXiv:1610.05586, 2016.
    [16] Shen W, Liu R. Learning residual images for face attribute manipulation. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 1225-1233.
    [17] Zhang Z, Song Y, Qi H. Age progression/regression by conditional adversarial autoencoder. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 4352-4360.
    [18] Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv Preprint arXiv:1511.06434, 2015.
    [19] Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X. Improved techniques for training GANs. In:Proc. of the Conf. and Workshop on Neural Information Processing Systems. 2016. 2226-2234.
    [20] Mathieu MF, Zhao JJ, Zhao J, Ramesh A, Sprechmann P, LeCun Y. Disentangling factors of variation in deep representation using adversarial training. In:Proc. of the Conf. and Workshop on Neural Information Processing Systems. 2016. 5040-5048.
    [21] Pathak D, Krahenbuhl P, Donahue J, Darrell T, Efros AA. Context encoders:Feature learning by inpainting. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2016. 2536-2544.
    [22] Mathieu M, Couprie C, LeCun Y. Deep multi-scale video prediction beyond mean square error. In:Proc. of the Int'l Conf. on Learning Representations. 2016. 2.
    [23] Vondrick C, Pirsiavash H, Torralba A. Generating videos with scene dynamics. In:Proc. of the Conf. and Workshop on Neural Information Processing Systems. 2016. 613-621.
    [24] Wu J, Zhang C, Xue T, Freeman B, Tenenbaum J. Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In:Proc. of the Conf. and Workshop on Neural Information Processing Systems. 2016. 82-90.
    [25] Gatys LA, Ecker AS, Bethge M. A neural algorithm of artistic style. arXiv Preprint arXiv:1508.06576, 2015.
    [26] Johnson J, Alahi A, Li FF. Perceptual losses for real-time style transfer and super-resolution. In:Proc. of the European Conf. on Computer Vision. Cham:Springer-Verlag, 2016. 694-711.
    [27] Fišer J, Jamriška O, Simons D, Shechtman E, Lu J, Asente P, Lukac M, Sýkora D. Example-based synthesis of stylized facial animations. ACM Trans. on Graphics (TOG), 2017,36(4):155.
    [28] Liao J, Yao Y, Yuan L, Hua G, Kang SB. Visual attribute transfer through deep image analogy. arXiv Preprint arXiv:1705.01088, 2017. 1, 2, 4, 6, 7, 8.
    [29] Sangkloy P, Lu J, Fang C, Yu F, Hays J. Scribbler:Controlling deep image synthesis with sketch and color. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2016. 6836-6845.
    [30] Bousmalis K, Silberman N, Dohan D, Erhan D, Krishnan D. Unsupervised pixel-level domain adaptation with generative adversarial networks. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2017,1(2):7.
    [31] Li Y, Song L, Wu X, He R, Tan T. Anti-makeup:Learning a bi-level adversarial network for makeup-invariant face verification. arXiv Preprint arXiv:1709.03654, 2017.
    [32] Wang S, Fu Y. Face behind makeup. In:Proc. of the AAAI Conf. on Artificial Intelligence. 2016. 58-64.
    [33] Li C, Zhou K, Lin S. Simulating makeup through physics-based manipulation of intrinsic image layers. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2015. 4621-4629.
    [34] Liu S, Ou X, Qian R, Wang W, Cao X. Makeup like a superstar:Deep localized makeup transfer network. In:Proc. of the Int'l Joint Conf. on Artificial Intelligence. 2016. 2568-2575.
    [35] Chang H, Lu J, Yu F, Finkelstein A. PairedCycleGAN:Asymmetric style transfer for applying and removing makeup. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2018. 40-48.
    [36] Odena A. Semi-supervised learning with generative adversarial networks. arXiv Preprint arXiv:1606.01583, 2016.
    [37] Odena A, Olah C, Shlens J. Conditional image synthesis with auxiliary classifier GANs. In:Proc. of the Int'l Conf. on Machine Learning. 2017. 2642-2651.
    [38] Reed S, Akata Z, Yan X, Logeswaran L, Schiele B, Lee H. Generative adversarial text to image synthesis. In:Proc. of the Int'l Conf. on Machine Learning. 2016. 1060-1069.
    [39] Zhang H, Xu T, Li H, Zhang S, Huang X, Wang X, Metaxas D. StackGAN:Text to photo-realistic image synthesis with stacked generative adversarial networks. arXiv Preprint arXiv:1612.03242, 2016,2(3):5.
    [40] Kim T, Cha M, Kim H, Lee JK, Kim J. Learning to discover cross-domain relations with generative adversarial networks. In:Proc. of the Int'l Conf. on Machine Learning. 2017. 1857-1865.
    [41] Taigman Y, Polyak A, Wolf L. Unsupervised cross-domain image generation. arXiv Preprint arXiv:1611.02200, 2016.
    [42] Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville AC. Improved training of wasserstein GANs. In:Proc. of the Int'l Conf. on Neural Information Processing Systems. 2017. 5767-5777.
    [43] Liu Z, Luo P, Wang X, Tang X. Deep learning face attributes in the wild. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2015. 2, 4, 6.
    [44] Choi Y, Choi M, Kim M, Ha JW, Kim S, Choo J. StarGAN:Unified generative adversarial networks for multi-domain image-to-image translation. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2018. 8789-8797.
    [45] Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. DeepLab:Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2018,40(4):834-848.
    [46] Mao X, Li Q, Xie H, Lau RY, Wang Z, Smolley SP. Least squares generative adversarial networks. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2017.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

包仁达,庾涵,朱德发,黄少飞,孙瑶,刘偲.基于区域敏感生成对抗网络的自动上妆算法.软件学报,2019,30(4):896-913

复制
分享
文章指标
  • 点击次数:3862
  • 下载次数: 5886
  • HTML阅读次数: 3305
  • 引用次数: 0
历史
  • 收稿日期:2018-04-16
  • 最后修改日期:2018-06-13
  • 在线发布日期: 2019-04-01
文章二维码
您是第19892581位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号