SadTalker：Stylized Audio( 七 ) _视频

[4] Y u Deng,Yang,Xu, Dong Chen, Y unde Jia, and Xin Tong.3d facewith - : Fromimage to image set.In CVPR , 2019. 2, 3, 4, 5, 12, 13, 14
[5] Carl .on. arXivarXiv:1606.05908, 2016. 2, 4
[6],, and. : One-shotheadand . In ICCV, 2021. 3
[7]Fan,Lin, Jun Saito,Wang, and Taku . : - 3dwith . In CVPR, 2022. 8
[8]P . ,,,,, and.-aware3dfrom . arXivarXiv:2207.11094, 2022. 4, 13
[9] Shiry , Amir Bar, Gefen ,Chan,Owens, andMalik.of. In CVPR, 2019. 7, 8, 14
[10] Y udong Guo, Keyu Chen, Sen Liang, Y ong-Jin Liu, Hujun Bao, andZhang. Ad-nerf: Audioforhead . In ICCV, 2021. 2
[11]He,Zhang,Ren, and Jian Sun.Deepfor image . In CVPR, 2016.4
[12],,,, and Sepp . Gansby a two time-scaleruleto a local nash .In , 2017. 5
[13] Fa-Ting Hong,Zhang, Li Shen, and Dan Xu.forhead video . In CVPR, 2022. 3
[14] Yang Hong, Bo Peng,Xiao,Liu, andZhang. : A real-time nerf-basedhead model. In CVPR, 2022. 8
[15]Isola, Jun-Y an Zhu,Zhou, andA Efros.Image-to-imagewith. CVPR, 2017. 14
[16] Xinya Ji, Hang Zhou,Wang,Wu, Wayne Wu, Feng Xu, and Xun Cao. Eamm: One-shotface via audio-based -awaremodel. In ACM , 2022. 2 [17] Xinya Ji, Hang Zhou,Wang, Wayne Wu, ChenLoy, Xun Cao, and Feng Xu. Audio-video . In CVPR, 2021. 3 [18]Kim, Pablo , Ayush ,Xu,Thies,,P′erez,,Zollh¨ofer, and. Deep video . ACMon(TOG), 2018.2
[19]Pand Jimmy Ba. Afor. arXivarXiv:1412.6980, 2014. 5
[20]Pand Max . Auto-bayes. CoRR, abs/1312.6114, 2014. 4
[21] Siyao Li, Y u , Gu , Lin , Wang Quan, Qian Chen, Loy Chen , and Liu Ziwei. : 3d dancevia actor- gpt with. In CVPR, 2022. 5
[22] YLu,Chai, and Xun Cao. Live: real-time-head . ACMon(TOG), 2021. 3
[23]Ma, YWang,, Jie Shen, and Maja .forlip-. In , 2022. 13 [24] Arun , Ting-Chun Wang, and Ming-Y u Liu.forwith Image Sets. In , 2022. 3
[25] Arsha , Joon Son Chung, and.V : a large-scale. In , 2017. 5, 11, 12
[26]D.and Lina J. Karam. A no- image blurbased on theof blur(cpbd). TIP, 2011. 5
[27] Ruiz , Eunji Chong, and Rehg James M. Fine- head pose. In CVPR , 2018. 5
[28] K R ,, Vinay P ., and C.V .. A lip syncis all you need forto lipin the wild. In ACM MM, 2020. 2, 3, 4, 5, 6, 7, 11, 12
[29]K R,, Jerin ,Jha, Vinay , and C V .face-to-face . In ACM MM, 2019. 2
[30],, Alex , Casey Chu, and Mark Chen.text- imagewith clip . arXivarXiv:2204.06125, 2022.9
[31] Y urui Ren, Ge Li, Y uanqi Chen,H Li, and Shan Liu. :imagevia. In ICCV, 2021. 2, 3, 5, 8, 11, 14
[32],Chan,, Lala Li, Jay Whang, Emily , SeyedSeyed , BurcuAyan, S Sara , RaphaLopes, et altext-to-imagewith deep. arXivarXiv:2205.11487, 2022. 9
[33]. -fid: FID Score for .
fid,2020. V0.2.1. 5
[34], St′ `ere,, Elisa Ricci, and Nicu Sebe. First ordermodel for image . In , 2019. 2, 3, 5, 11
[35],, Jian Ren,Chai, and.for. In CVPR, 2021. 3
[36]Thies,, Ayush ,, andNie?ner.voice : Audio-. In ECCV, 2020. 2
[37]Wang,Li, Y u Ding,Fan, and Xin Y u. : Audio- one-shot -headwithhead . In IJCAI, 2021. 2, 5, 6, 7, 12
[38]Wang,Li, Y u Ding, and Xin Y u.facefrom - audio-. In AAAI, 2022. 2, 5, 6, 7, 12
[39] Ting-Chun Wang, Ming-Y u Liu,Tao,Liu, Jan Kautz, and Bryan . Few-shot video-to-video . In , 2019. 3
[40] Ting-Chun Wang, Arun , and Ming-Y u Liu. One-shot free-view-headfor video . In CVPR, 2021. 2, 3, 4, 5, 8, 11, 14
[41]Wang, Y u Li,Zhang, and Ying Shan.real-world blind facewithprior. In CVPR, 2021. 8 [42]Wang, Di Yang,, and.image :toviaspace . arXivarXiv:2203.09043, 2022. 3
[43] Xin Wen, Miao Wang,, Ze-Yin Chen, and Shi-Min Hu.audio- video .IEEEonand, 26(12):3457–3466, 2020. 2, 8
[44] Fei Yin, Y ong Zhang,Cun,Cao, Y anbo Fan, Xuan Wang,Bai,Wu, Jue Wang, and Y ujiu Yang. : One-shot high-facevia pre- . In ECCV, 2022. 3
[45]Zhang, Yifan Zhao, Yifei Huang, Ming Zeng,Ni,, andGuo. :face with. In ICCV, 2021. 3
[46]Zhang,Li, Y u Ding, andFan.Flow- one-shotfacewith aaudio- . In CVPR, 2021. 2, 5, 11, 12
[47] Jian Zhao and Hui Zhang. Thin-platemodel for image . In CVPR, 2022. 3