人脸合成技术综述

doi:10.3778/j.issn.1673-9418.2105059

摘要/Abstract

摘要：

人脸合成由于其应用与技术价值，是机器视觉领域的热点之一，而近年来深度学习的突破性进展使该领域吸引了更多关注。将该领域的研究分为四个子类：人脸身份合成、人脸动作合成、人脸属性合成与人脸生成，并系统地总结了这些子类的发展历程、现状，以及现有技术存在的问题。首先针对人脸身份合成，从图形学、数字图像处理与深度学习三个角度总结了各自的合成流程，对关键技术原理进行了详细的解释与分析。其次将人脸动作合成进一步分为利用标签驱动的表情编辑与利用真实人脸驱动的人脸重演，并指出了各自领域中存在的缺陷与难题。然后介绍了基于生成模型，尤其是生成对抗网络在人脸属性合成方面的发展，最终对人脸生成的各类工作进行了简单的阐述。此外，介绍了人脸合成技术的实际应用与当前面临的相关问题，并展望了该领域未来可能的研究方向。

关键词: 人脸合成, 生成对抗网络（GAN）, 深度学习

Abstract:

Face synthesis is one of the hot topics in the field of computer vision because of its application and technical value. In recent years, the breakthrough of deep learning has attracted much attention in this field. This paper divides the research in this field into four subcategories: face identity synthesis, face movements synthesis, face attributes synthesis and face generation, and systematically summarizes the development process, status quo, and existing problems of these subcategories. First of all, for face identity synthesis, three approaches are summarized, including computer graphics, digital image processing and deep learning. This paper summarizes their respective routine processes, and analyzes the technical principles of milestone work in detail. Secondly, face movements synthesis is further divided into label driven expression editing and real face driven face reenactment, where the shortcomings and problems in each field are pointed out. Then, the development of face attribute synthesis based on generative model is introduced, especially generative adversarial network. Finally, this paper briefly describes all kinds of researches on face generation. In addition, this paper also introduces the practical application and related problems of face synthesis field and provides the possible research direction in this field.

Key words: face synthesis, generative adversarial network (GAN), deep learning

费建伟，夏志华，余佩鹏，戴昀书. 人脸合成技术综述[J]. 计算机科学与探索, 2021, 15(11): 2025-2047.

FEI Jianwei, XIA Zhihua, YU Peipeng, DAI Yunshu. Survey of Face Synthesis[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(11): 2025-2047.

参考文献

[1] LIANG R G, LV P Z, ZHAO Y, et al. A survey of audio-visual deepfake detection techniques[J]. Journal of Cyber Security, 2020, 5(2): 1-17.
梁瑞刚, 吕培卓, 赵月, 等. 视听觉深度伪造检测技术研究综述[J]. 信息安全学报, 2020, 5(2): 1-17.
[2] MIN F, LU T W, ZHANG Y D. Automatic face replacement in photographs based on active shape models[C]//Proceed-ings of the 2009 Asia-Pacific Conference on Computational Intelligence and Industrial Applications, Wuhan, Nov 28-29, 2009. Piscataway: IEEE, 2009: 170-173.
[3] Welcome to Chechnya[EB/OL]. [2021-07-12]. https://www.welcometochechnya.com.
[4] Insecam[EB/OL]. [2021-07-12]. https://www.insecam.org.
[5] BORSHUKOV G, PIPONI D, LARSEN O, et al. Universal capture: image-based facial animation for “the matrix relo-aded”[C]//Proceedings of the 2005 International Conference on Computer Graphics and Interactive Techniques, Los An-geles, Jul 31-Aug 4, 2005. New York: ACM, 2005: 16.
[6] JOSHI N, MATUSIK W, ADELSON E H, et al. Personal photo enhancement using example images[J]. ACM Trans-actions on Graphics, 2010, 29(2): 12.
[7] LEYVAND T, COHEN-OR D, DROR G, et al. Data-driven enhancement of facial attractiveness[J]. ACM Transactions on Graphics, 2008, 27(3): 38.
[8] NARUNIEC J, HELMINGER L, SCHROERS C, et al. High-resolution neural face swapping for visual effects[J]. Com-puter Graphics Forum, 2020, 39(4): 173-184.
[9] ZHANG J N, ZENG X F, WANG M M, et al. FreeNet: multi-identity face reenactment[C]//Proceedings of the 2020 IEEE/ CVF Conference on Computer Vision and Pattern Recogni-tion, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 5325-5334.
[10] LUO C W, YU J, WANG Z F. Synthesizing performance-driven facial animation[J]. Acta Automatica Sinica, 2014, 40(10): 2245-2252.
罗常伟, 於俊, 汪增福. 视频驱动人脸动画合成[J]. 自动化学报, 2014, 40(10): 2245-2252.
[11] H.R.3600-Deepfakes report act of 2019[EB/OL]. [2021-07-12]. https://www.congress.gov/bill/116th-congress/house-bill/3600.
[12] 网络音视频信息服务管理规定[EB/OL]. [2021-07-12]. http://www.cac.gov.cn/2019-11/29/c_1576561820967678.htm.
[13] ALEXANDER O, ROGERS M, LAMBETH W, et al. Creat-ing a photoreal digital actor: the digital emily project[C]// Proceedings of the 2009 Conference for Visual Media Pro-duction, London, Nov 12-13, 2009. Piscataway: IEEE, 2009: 176-187.
[14] CAI L, GUO Y D, ZHANG J Y. High-quality 3D face recon-struction from multi-view images[J]. Journal of Computer-Aided Design & Computer Graphics, 2020, 32(2): 305-314.
蔡麟, 郭玉东, 张举勇. 基于多视角的高精度三维人脸重建[J]. 计算机辅助设计与图形学学报, 2020, 32(2): 305-314.
[15] BLANZ V, VETTER T. A morphable model for the synthesis of 3D faces[C]//Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, Los An-geles, Aug 8-13, 1999. New York: ACM, 1999: 187-194.
[16] CAO C, WENG Y L, ZHOU S, et al. Facewarehouse: a 3D facial expression database for visual computing[J]. IEEE Transactions on Visualization and Computer Graphics, 2013, 20(3): 413-425.
[17] PAYSAN P, KNOTHE R, AMBERG B, et al. A 3D face model for pose and illumination invariant face recognition [C]//Proceedings of the 6th IEEE International Conference on Advanced Video and Signal Based Surveillance, Genova, Sep 2-4, 2009. Washington: IEEE Computer Society, 2009: 296-301.
[18] BOOTH J, ROUSSOS A, PONNIAH A, et al. Large scale 3D morphable models[J]. International Journal of Computer Vision, 2018, 126(2): 233-254.
[19] ROMDHANI S, VETTER T. Estimating 3D shape and tex-ture using pixel intensity, edges, specular highlights, texture constraints and a prior[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pat-tern Recognition, San Diego, Jun 20-26, 2005. Washington: IEEE Computer Society, 2005: 986-993.
[20] AMBERG B, BLAKE A, FITZGIBBON A W, et al. Recons-tructing high quality face-surfaces using model based stereo [C]//Proceedings of the 11th International Conference on Computer Vision, Rio de Janeiro, Oct 14-20, 2007. Wash-ington: IEEE Computer Society, 2007: 1-8.
[21] YE Z P, XIA W Y, SUN Z Y, et al. From traditional rendering to differentiable rendering: theories, methods and applications[J]. Science China: Information Sciences, 2021, 51(7): 1043-1067.
叶子鹏, 夏雯宇, 孙志尧, 等. 从传统渲染到可微渲染: 基本原理、方法和应用[J]. 中国科学: 信息科学, 2021, 51(7): 1043-1067.
[22] TUAN TRAN A, HASSNER T, MASI I, et al. Regressing robust and discriminative 3D morphable models with a very deep neural network[C]//Proceedings of the 2017 IEEE Con-ference on Computer Vision and Pattern Recognition, Hon-olulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 1493-1502.
[23] CHEN A P, CHEN Z, ZHANG G L, et al. Photo-realistic facial details synthesis from single image[C]//Proceedings of the 2019 IEEE/CVF International Conference on Com-puter Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 9428-9438.
[24] GECER B, PLOUMPIS S, KOTSIA I, et al. GANFIT: gen-erative adversarial network fitting for high fidelity 3D face reconstruction[C]//Proceedings of the 2019 IEEE/CVF Con-ference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 1155-1164.
[25] DENG Y, YANG J L, XU S C, et al. Accurate 3D face re-construction with weakly-supervised learning: from single image to image set[C]//Proceedings of the 2019 IEEE Con-ference on Computer Vision and Pattern Recognition Work-shops, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 285-295.
[26] YU Z P, CHI J, YE Y N, et al. Detailed features-preserving 3D facial expression transfer[J]. Journal of Computer-Aided Design & Computer Graphics, 2021, 33(2): 186-198.
于志平, 迟静, 叶亚男, 等. 细节特征保持的三维面部表情迁移方法[J]. 计算机辅助设计与图形学学报, 2021, 33(2): 186-198.
[27] VLASIC D, BRAND M, PFISTER H, et al. Face transfer with multilinear models[C]//Proceedings of the 2006 Inter-national Conference on Computer Graphics and Interactive Techniques, Boston, Jul 30-Aug 3, 2006. New York: ACM, 2006: 24.
[28] THIES J, ZOLLH?FER M, NIE?NER M, et al. Real-time expression transfer for facial reenactment[J]. ACM Transac-tions on Graphics, 2015, 34(6): 183.
[29] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2014, Montreal, Dec 8-13, 2014. Red Hook: Curran Associates, 2014: 2672-2680.
[30] WANG K F, GOU C, DUAN Y J, et al. Generative adversarial networks: the state of the art and beyond[J]. Acta Automa-tica Sinica, 2017, 43(3): 321-332.
王坤峰, 苟超, 段艳杰, 等. 生成式对抗网络GAN的研究进展与展望[J]. 自动化学报, 2017, 43(3): 321-332.
[31] MIRZA M, OSINDERO S. Conditional generative adversa-rial nets[J]. arXiv:1411.1784, 2014.
[32] ODENA A, OLAH C, SHLENS J. Conditional image synth-esis with auxiliary classifier GANs[C]//Proceedings of the 34th International Conference on Machine Learning, Sydney, Aug 6-11, 2017: 2642-2651.
[33] PERARNAU G, VAN DE WEIJER J, RADUCANU B, et al. Invertible conditional GANs for image editing[J]. arXiv: 1611.06355, 2016.
[34] CHEN X, DUAN Y, HOUTHOOFT R, et al. InfoGAN: inter-pretable representation learning by information maximizing generative adversarial nets[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2016, Barcelona, Dec 5-10, 2016. Red Hook: Curran Associates, 2016: 2172-2180.
[35] DENTON E L, CHINTALA S, SZLAM A, et al. Deep gen-erative image models using a Laplacian pyramid of adver-sarial networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Dec 7-12, 2015. Red Hook: Curran Associates, 2015: 1486-1494.
[36] KARRAS T, AILA T, LAINE S, et al. Progressive growing of GANs for improved quality, stability, and variation[C]// Proceedings of the 6th International Conference on Learn-ing Representations, Vancouver, Apr 30-May 3, 2018: 1-26.
[37] KARRAS T, LAINE S, AILA T. A style-based generator architecture for generative adversarial networks[C]//Procee-dings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Pis-cataway: IEEE, 2019: 4401-4410.
[38] ISOLA P, ZHU J Y, ZHOU T H, et al. Image-to-image tran-slation with conditional adversarial networks[C]//Proceed-ings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 5967-5976.
[39] WANG T C, LIU M Y, ZHU J Y, et al. High-resolution image synthesis and semantic manipulation with conditional GANs [C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 8798-8807.
[40] MALIK S. Digital face replacement in photographs[R]. Toronto: University of Toronto, 2003.
[41] BLANZ V, SCHERBAUM K, VETTER T, et al. Exchang-ing faces in images[J]. Computer Graphics Forum, 2004, 23(3): 669-676.
[42] CHENG Y T, TZENG V, LIANG Y, et al. 3D-model-based face replaement in video[C]//Proceedings of the 2009 Inter-national Conference on Computer Graphics and Interactive Techniques, New Orleans, Aug 3-7, 2009. New York: ACM, 2009: 1.
[43] LIN Y, LIN Q, TANG F, et al. Face replacement with large-pose differences[C]//Proceedings of the 20th ACM Multi-media Conference, Nara, Oct 29-Nov 2, 2012. New York: ACM, 2012: 1249-1250.
[44] LIN Y, WANG S J, LIN Q, et al. Face swapping under large pose variations: a 3D model based approach[C]//Proceedings of the 2012 IEEE International Conference on Multimedia and Expo, Melbourne, Jul 9-13, 2012. Washington: IEEE Computer Society, 2012: 333-338.
[45] DALE K, SUNKAVALLI K, JOHNSON M K, et al. Video face replacement[J]. ACM Transactions on Graphics, 2011, 30(6): 130.
[46] PéREZ P, GANGNET M, BLAKE A. Poisson image editing[J]. ACM Transactions on Graphics, 2003, 22(3): 313-318.
[47] CHEN T, CHENG M M, TAN P, et al. Sketch2photo: Internet image montage[J]. ACM Transactions on Graphics, 2009, 28(5): 124.
[48] BOYKOV Y, JOLLY M P. Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images [C]//Proceedings of the 8th International Conference on Computer Vision, Vancouver, Jul 7-14, 2001. Washington: IEEE Computer Society, 2001: 105-112.
[49] BITOUK D, KUMAR N, DHILLON S, et al. Face swap-ping: automatically replacing faces in photographs[J]. ACM Transactions on Graphics, 2008, 27(3): 39.
[50] MOSADDEGH S, SIMON L, JURIE F. Photorealistic face de-identification by aggregating donors?? face components[C]// LNCS 9005: Proceedings of the 2nd Asian Conference on Computer Vision, Singapore, Nov 1-5, 2014. Cham: Springer, 2014: 159-174.
[51] KEMELMACHER-SHLIZERMAN I. Transfiguring portraits[J]. ACM Transactions on Graphics, 2016, 35(4): 94.
[52] COOTES T F, TAYLOR C J, COOPER D H, et al. Active shape models-their training and application[J]. Computer Vision and Image Understanding, 1995, 61(1): 38-59.
[53] WANG H X, PAN C H, GONG H F, et al. Facial image com-position based on active appearance model[C]//Proceedings of the 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing, Las Vegas, Mar 30-Apr 4, 2008. Piscataway: IEEE, 2008: 893-896.
[54] COOTES T F, EDWARDS G J, TAYLOR C J. Active app-earance models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): 681-685.
[55] GARRIDO P, VALGAERTS L, REHMSEN O, et al. Auto-matic face reenactment[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Jun 23-28, 2014. Washington: IEEE Computer Society, 2014: 4217-4224.
[56] CHEN T, TAN P, MA L Q, et al. PoseShop: human image database construction and personalized content synthesis[J]. IEEE Transactions on Visualization and Computer Graphics, 2012, 19(5): 824-837.
[57] SUNKAVALLI K, JOHNSON M K, MATUSIK W, et al. Multi-scale image harmonization[J]. ACM Transactions on Graphics, 2010, 29(4): 125.
[58] ZHANG X J, SONG J, PARK J I. The image blending me-thod for face swapping[C]//Proceedings of the 4th IEEE In-ternational Conference on Network Infrastructure and Digital Content, Beijing, Sep 19-21, 2014. Piscataway: IEEE, 2014: 95-98.
[59] YAN S, HE S, LEI X, et al. Video face swap based on auto-encoder generation network[C]//Proceedings of the 2018 International Conference on Audio, Language and Image Processing, Shanghai, Jul 16-17, 2018. Piscataway: IEEE, 2018: 103-108.
[60] KORSHUNOVA I, SHI W Z, DAMBRE J, et al. Fast face-swap using convolutional neural networks[C]//Proceedings of the 2017 IEEE International Conference on Computer Vi-sion, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 3677-3685.
[61] JOHNSON J, ALAHI A, LI F F. Perceptual losses for real-time style transfer and super-resolution[C]//LNCS 9906: Proceedings of the 14th European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Cham: Springer, 2016: 694-711.
[62] ULYANOV D, LEBEDEV V, VEDALDI A, et al. Texture networks: feed-forward synthesis of textures and stylized images[C]//Proceedings of the 33nd International Conference on Machine Learning, New York, Jun 19-24, 2016: 2027-2041.
[63] LI L Z, BAO J M, YANG H, et al. Advancing high fidelity identity swapping for forgery detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 5073-5082.
[64] NIRKIN Y, MASI I, TUAN A T, et al. On face segmentation, face swapping, and face perception[C]//Proceedings of the 13th IEEE International Conference on Automatic Face & Gesture Recognition, Xi??an, May 15-19, 2018. Washington: IEEE Computer Society, 2018: 98-105.
[65] NIRKIN Y, KELLER Y, HASSNER T. FSGAN: subject ag-nostic face swapping and reenactment[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 7183-7192.
[66] DONG H, NEEKHARA P, WU C, et al. Unsupervised image-to-image translation with generative adversarial networks[J]. arXiv:1701.02676, 2017.
[67] OLSZEWSKI K, LI Z M, YANG C, et al. Realistic dyna-mic facial textures from a single image using GANs[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 5439-5448.
[68] NATSUME R, YATAGAWA T, MORISHIMA S. RSGAN: face swapping and editing using face and hair representa-tion in latent spaces[C]//Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference, Vancouver, Aug 12-16, 2018. New York: ACM,2018: 69.
[69] NATSUME R, YATAGAWA T, MORISHIMA S. FSNet: an identity-aware generative model for image-based face swap-ping[C]//LNCS 11366: Proceedings of the 14th Asian Con-ference on Computer Vision, Perth, Dec 2-6, 2018. Cham: Springer, 2018: 117-132.
[70] BAO J M, CHEN D, WEN F, et al. Towards open-set iden-tity preserving face synthesis[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recogni-tion, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 6713-6722.
[71] LI Z W, LI Z M, FEI T L, et al. Face image restoration based on residual generative adversarial network[J]. Computer Science, 2020, 47(S1): 230-236.
李泽文, 李子铭, 费天禄, 等. 基于残差生成对抗网络的人脸图像复原[J]. 计算机科学, 2020, 47(S1): 230-236.
[72] PUMAROLA A, AGUDO A, MARTINEZ A M, et al. GAN-imation: anatomically-aware facial animation from a single image[C]//LNCS 11214: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 818-833.
[73] PUMAROLA A, AGUDO A, MARTINEZ A M, et al. GAN-imation: one-shot anatomically consistent facial animation[J]. International Journal of Computer Vision, 2020, 128(3): 698-713.
[74] SANCHEZ E, VALSTAR M. Triple consistency loss for pairing distributions in GAN-based face synthesis[J]. arXiv:1811.03492, 2018.
[75] PHAM H X, WANG Y, PAVLOVIC V. Generative adversa-rial talking head: bringing portraits to life with a weakly supervised neural network[J]. arXiv:1803.07716, 2018.
[76] ZHOU Y Q, SHI B E. Photorealistic facial expression synth-esis by the conditional difference adversarial autoencoder[C]//Proceedings of the 7th International Conference on Affective Computing and Intelligent Interaction, San Ant-onio, Oct 23-26, 2017. Washington: IEEE Computer Society, 2017: 370-376.
[77] BOZORGTABAR B, RAD M S, EKENEL H K, et al. Us-ing photorealistic face synthesis and domain adaptation to improve facial expression analysis[C]//Proceedings of the 14th IEEE International Conference on Automatic Face & Gesture Recognition Lille, May 14-18, 2019. Piscataway: IEEE, 2019: 1-8.
[78] DING H, SRICHARAN K, CHELLAPPA R. ExprGAN: fa-cial expression editing with controllable expression intensity[C]//Proceedings of the 32nd AAAI Conference on Artifi-cial Intelligence, the 30th Innovative Applications of Artifi-cial Intelligence, and the 8th AAAI Symposium on Educa-tional Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 6781-6788.
[79] PIGHIN F H, HECKER J, LISCHINSKI D, et al. Synthesi-zing realistic facial expressions from photographs[C]//Pro-ceedings of the 2006 International Conference on Computer Graphics and Interactive Techniques, Boston, Jul 30-Aug 3, 2006. New York: ACM, 2006: 19.
[80] DE LA HUNTY M, ASTHANA A, GOECKE R. Linear facial expression transfer with active appearance models[C]//Proceedings of the 20th International Conference on Pattern Recognition, Istanbul, Aug 23-26, 2010. Washington: IEEE Computer Society, 2010: 3789-3792.
[81] THEOBALD B J, MATTHEWS I, MANGINI M, et al. Map-ping and manipulating facial expression[J]. Language and Speech, 2009, 52(2/3): 369-386.
[82] LIU Z C, SHAN Y, ZHANG Z Y. Expressive expression mapping with ratio images[C]//Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, Los Angeles, Aug 12-17, 2001. New York: ACM, 2001: 271-276.
[83] BREGLER C, COVELL M, SLANEY M. Video rewrite: driving visual speech with audio[C]//Proceedings of the 24th Annual Conference on Computer Graphics and Interac-tive Techniques, Los Angeles, Aug 3-8, 1997. New York: ACM, 1997: 353-360.
[84] SUWAJANAKORN S, SEITZ S M, KEMELMACHER-SHLIZERMAN I. Synthesizing Obama: learning lip sync from audio[J]. ACM Transactions on Graphics, 2017, 36(4): 95.
[85] YANG F, WANG J, SHECHTMAN E, et al. Expression flow for 3D-aware face component transfer[J]. ACM Transactions on Graphics, 2011, 30(4): 60.
[86] BLANZ V, BASSO C, POGGIO T A, et al. Reanimating faces in images and video[J]. Computer Graphics Forum, 2003, 22(3): 641-650.
[87] WILLIAMS L. Performance-driven facial animation[C]// Proceedings of the 17th Annual Conference on Computer Graphics and Interactive Techniques, Dallas, Aug 6-10, 1990. New York: ACM, 1990: 235-242.
[88] GARRIDO P, VALGAERTS L, SARMADI H, et al. VDub: modifying face video of actors for plausible visual align-ment to a dubbed audio track[J]. Computer Graphics Forum, 2015, 34(2): 193-204.
[89] SUWAJANAKORN S, SEITZ S M, KEMELMACHER-SHLIZERMAN I. What makes Tom Hanks look like Tom Hanks[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Dec 7-13, 2015. Washington: IEEE Computer Society, 2015: 3952-3960.
[90] YAN Y F, LYU K, XUE J, et al. Facial animation method based on deep learning and expression AU parameters[J]. Journal of Computer-Aided Design & Computer Graphics, 2019, 31(11): 1973-1980.
闫衍芙, 吕科, 薛健, 等. 基于深度学习和表情AU参数的人脸动画方法[J]. 计算机辅助设计与图形学学报, 2019, 31(11): 1973-1980.
[91] THIES J, ZOLLH?FER M, STAMMINGER M, et al. Face2-Face: real-time face capture and reenactment of RGB videos[C]//Proceedings of the 2016 IEEE Conference on Com-puter Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 2387-2395.
[92] THIES J, ZOLLH?FER M, STAMMINGER M, et al. Face-VR: real-time gaze-aware facial reenactment in virtual rea-lity[J]. ACM Transactions on Graphics, 2018, 37(2): 25.
[93] THIES J, ZOLLH?FER M, THEOBALT C, et al. Headon: real-time reenactment of human portrait videos[J]. ACM Transactions on Graphics, 2018, 37(4): 164.
[94] AVERBUCH-ELOR H, COHEN-OR D, KOPF J, et al. Br-inging portraits to life[J]. ACM Transactions on Graphics, 2017, 36(6): 196.
[95] THIES J, ZOLLH?FER M, NIE?NER M. Deferred neural rendering: image synthesis using neural textures[J]. ACM Transactions on Graphics, 2019, 38(4): 66.
[96] KIM H, GARRIDO P, TEWARI A, et al. Deep video por-traits[J]. ACM Transactions on Graphics, 2018, 37(4): 163.
[97] KOUJAN M R, DOUKAS M C, ROUSSOS A, et al. Head2-Head: video-based neural head synthesis[C]//Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition, Buenos Aires, Nov 16-20, 2020. Piscataway: IEEE, 2020: 16-23.
[98] DOUKAS M C, KOUJAN M R, SHARMANSKA V, et al. Head2Head++: deep facial attributes re-targeting[J]. IEEE Transactions on Biometrics, Behavior, and Identity Science,2021, 3(1): 31-43.
[99] NAGANO K, SEO J, XING J, et al. paGAN: real-time ava-tars using dynamic textures[J]. ACM Transactions on Grap-hics, 2018, 37(6): 258.
[100] ZAKHAROV E, SHYSHEYA A, BURKOV E, et al. Few-shot adversarial learning of realistic neural talking head models[C]//Proceedings of the 2019 IEEE/CVF Interna-tional Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 9459-9468.
[101] GENG J, SHAO T, ZHENG Y, et al. Warp-guided GANs for single-photo facial animation[J]. ACM Transactions on Graphics, 2018, 37(6): 231.
[102] WILES O, KOEPKE A S, ZISSERMAN A. X2Face: a net-work for controlling face generation using images, audio, and pose codes[C]//LNCS 11217: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 670-686.
[103] SIAROHIN A, LATHUILIèRE S, TULYAKOV S, et al. Animating arbitrary objects via deep motion transfer[C]// Proceedings of the 2019 IEEE/CVF Conference on Com-puter Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 2377-2386.
[104] SIAROHIN A, LATHUILIèRE S, TULYAKOV S, et al. First order motion model for image animation[C]//Procee-dings of the Annual Conference on Neural Information Processing Systems 2019, Vancouver, Dec 8-14, 2019: 7137-7147.
[105] FU Y, GUO G, HUANG T S. Age synthesis and estimation via faces: a survey[J]. IEEE Transactions on Pattern Anal-ysis and Machine Intelligence, 2010, 32(11): 1955-1976.
[106] LI M, ZUO W M, ZHANG D. Deep identity-aware transfer of facial attributes[J]. arXiv:1610.05586, 2016.
[107] SHEN W, LIU R J. Learning residual images for face attri-bute manipulation[C]//Proceedings of the 2017 IEEE Con-ference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 1225-1233.
[108] KAPANIA S, GOYAL S, LAMBA S, et al. Multiple do-main image to image translation for facial attribute trans-fer[J]. International Journal of Information Systems & Management Science, 2019, 2(2).
[109] SHEN Y J, GU J J, TANG X O, et al. Interpreting the latent space of GANs for semantic face editing[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Pisca-taway: IEEE, 2020: 9243-9252.
[110] ZHU J Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 2242-2251.
[111] HE Z L, ZUO W M, KAN M N, et al. AttGAN: facial att-ribute editing by only changing what you want[J]. IEEE Transactions on Image Processing, 2019, 28(11): 5464-5478.
[112] LIU M, DING Y K, XIA M, et al. STGAN: a unified selec-tive transfer network for arbitrary image attribute editing[C]//Proceedings of the 2019 IEEE Conference on Com-puter Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 3673-3682.
[113] ZHU D, LIU S, JIANG W, et al. UGAN: untraceable GAN for multi-domain face translation[J]. arXiv:1907.11418, 2019.
[114] CHOI Y, CHOI M, KIM M, et al. StarGAN: unified gen-erative adversarial networks for multi-domain image-to-image translation[C]//Proceedings of the 2018 IEEE Con-ference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 8789-8797.
[115] LIU Y, FAN H, NI F C, et al. ClsGAN: selective attribute editing model based on classification adversarial network[J]. Neural Networks, 2021, 133: 220-228.
[116] HUANG Z K, ZHENG Z D, YAN C G, et al. Real-world automatic makeup via identity preservation makeup net[C]//Proceedings of the 29th International Joint Confer-ence on Artificial Intelligence, Yokohama, Jul 2020: 652-658.
[117] JIN X, HAN R, NING N, et al. Facial makeup transfer combining illumination transfer[J]. IEEE Access, 2019, 7: 80928-80936.
[118] QIAN S J, LIN K, WU W, et al. Make a face: towards arbi-trary high fidelity face manipulation[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 10032-10041.
[119] LIU M, BREUEL T M, KAUTZ J. Unsupervised image-to-image translation networks[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2017, Long Beach, Dec 4-9, 2017. Red Hook: Curran Ass-ociates, 2017: 700-708.
[120] LAMPLE G, ZEGHIDOUR N, USUNIER N, et al. Fader networks: manipulating images by sliding attributes[C]// Proceedings of the Annual Conference on Neural Info-rmation Processing Systems 2017, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 5967-5976.
[121] SHU Z X, YUMER E, HADAP S, et al. Neural face edit-ing with intrinsic image disentangling[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Patt-ern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 5444-5453.
[122] KINGMA D P, DHARIWAL P. Glow: generative flow with invertible 1×1 convolutions[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2018, Montréal, Dec 3-8, 2018: 10236-10245.
[123] YIN W D, LIU Z W, LOY C C. Instance-level facial attri-butes transfer with geometry-aware flow[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, the 31st Innovative Applications of Artificial Intelligence Conference, the 9th AAAI Symposium on Educational Ad-vances in Artificial Intelligence, Honolulu, Jan 27-Feb 1, 2019. Menlo Park: AAAI, 2019: 9111-9118.
[124] BROCK A, DONAHUE J, SIMONYAN K. Large scale GAN training for high fidelity natural image synthesis[C]// Proceedings of the 7th International Conference on Learn-ing Representations, New Orleans, May 6-9, 2019: 1-35.
[125] KARRAS T, LAINE S, AITTALA M, et al. Analyzing and improving the image quality of styleGAN[C]//Proceed-ings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 8107-8116.
[126] KARNEWAR A, WANG O. Msg-GAN: multi-scale gradi-ents for generative adversarial networks[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Pisca-taway: IEEE, 2020: 7796-7805.
[127] HU Y K, FAN X, YU L T, et al. Graph based neural net-work regression strategy for facial image super resolution[J]. Journal of Software, 2018, 29(4): 914-925.
呼延康, 樊鑫, 余乐天, 等. 图神经网络回归的人脸超分辨率重建[J]. 软件学报, 2018, 29(4): 914-925.
[128] XU R B, LU T, WANG Y, et al. Face hallucination algori-thm via combined learning[J]. Journal of Computer Appli-cations, 2020, 40(3): 710-716.
许若波, 卢涛, 王宇, 等. 基于组合学习的人脸超分辨率算法[J]. 计算机应用, 2020, 40(3): 710-716.
[129] CHEN Y, TAI Y, LIU X M, et al. FSRNet: end-to-end learn-ing face super-resolution with facial priors[C]//Proceed-ings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 2492-2501.
[130] IIZUKA S, SIMO-SERRA E, ISHIKAWA H. Globally and locally consistent image completion[J]. ACM Transactions on Graphics, 2017, 36(4): 107.
[131] CHEN Z Y, NIE S L, WU T F, et al. High resolution face completion with multiple controllable attributes via fully end-to-end progressive generative adversarial networks[J]. arXiv:1801.07632, 2018.
[132] ZHANG L Z, WANG J C, XU Y S, et al. Nested scale-editing for conditional image synthesis[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Pisca-taway: IEEE, 2020: 5476-5486.
[133] ZHOU H Q, CAO L, DU K N. Sketch face synthesis based on multi-discriminator cyclic generative adversarial net-work[J]. Computer Engineering and Applications, 2021, 57(3): 231-238.
周华强, 曹林, 杜康宁. 多判别器循环生成对抗网络的素描人脸合成[J]. 计算机工程与应用, 2021, 57(3): 231-238.
[134] JIANG B, LIU H Y, YANG C, et al. A face inpainting algo-rithm with local attribute generative adversarial network[J]. Journal of Computer Research and Development, 2019, 56(11): 2485-2493.
蒋斌, 刘虹雨, 杨超, 等. 一种基于局部属性生成对抗网络的人脸修复算法[J]. 计算机研究与发展, 2019, 56(11): 2485-2493.
[135] ZHANG H, XU T, LI H S, et al. StackGAN: text to photo-realistic image synthesis with stacked generative adversa-rial networks[C]//Proceedings of the 2017 IEEE Interna-tional Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 5908-5916.
[136] ZHANG H, XU T, LI H S, et al. StackGAN++: realistic image synthesis with stacked generative adversarial net-works[J]. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence, 2018, 41(8): 1947-1962.
[137] NASIR O R, JHA S K, GROVER M S, et al. Text2FaceGAN: face generation from fine grained textual descriptions[C]// Proceedings of the 5th IEEE International Conference on Multimedia Big Data, Singapore, Sep 11-13, 2019. Pis-cataway: IEEE, 2019: 58-67.
[138] CHEN X, QING L B, HE X H, et al. FTGAN: a fully-trained generative adversarial networks for text to face generation[J]. arXiv:1904.05729, 2019.
[139] DI X, PATEL V M. Face synthesis from visual attributes via sketch using conditional VAEs and GANs[J]. arXiv: 1801.00077, 2017.
[140] BAO J M, CHEN D, WEN F, et al. CVAE-GAN: fine-grained image generation through asymmetric training[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 2764-2773.
[141] WANG T R, ZHANG T, LOVELL B C. Faces à la Carte: text-to-face generation via attribute disentanglement[C]// Proceedings of the 2021 IEEE Winter Conference on App-lications of Computer Vision, Waikoloa, Jan 3-8, 2021. Piscataway: IEEE, 2021: 3379-3387.
[142] LU Y Y, WU S Z, TAI Y W, et al. Image generation from sketch constraint using contextual GAN[C]//LNCS 11220: Proceedings of the 15th European Conference on Com-puter Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 213-228.
[143] SANGKLOY P, LU J W, FANG C, et al. Scribbler: control-ling deep image synthesis with sketch and color[C]//Pro-ceedings of the 2017 IEEE Conference on Computer Vis-ion and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 6836-6845.
[144] KAZEMI H, IRANMANESH M, DABOUEI A, et al. Fa-cial attributes guided deep sketch-to-photo synthesis[C]// Proceedings of the 2018 IEEE Winter Applications of Computer Vision Workshops, Lake Tahoe, Mar 15, 2018. Washington: IEEE Computer Society, 2018: 1-8.
[145] CHEN S Y, SU W C, GAO L, et al. Deep generation of face images from sketches[J]. arXiv:2006.01047, 2020.
[146] WANG T C, LIU M Y, ZHU J Y, et al. Video-to-video synthesis[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2018, Montréal, Dec 3-8, 2018: 1152-1164.
[147] JO Y, PARK J. SC-FEGAN: face editing generative adver-sarial network with user??s sketch and color[C]//Proceed-ings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 1745-1753.
[148] LIU C T, CAO L, DU K N. Portrait coloring based on joint consistent cyclic generative adversarial network[J]. Computer Engineering and Applications, 2020, 56(16): 183-190.
刘昌通, 曹林, 杜康宁. 基于联合一致循环生成对抗网络的人像着色[J]. 计算机工程与应用, 2020, 56(16): 183-190.