{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T10:44:05Z","timestamp":1770979445351,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Beijing Science and Technology Plan Project","award":["Z231100005923033"],"award-info":[{"award-number":["Z231100005923033"]}]},{"name":"Chinese National Natural Science Foundation Projects","award":["62176256, U23B2054, 62276254, 62106264"],"award-info":[{"award-number":["62176256, U23B2054, 62276254, 62106264"]}]},{"name":"InnoHK program"},{"name":"Beijing Natural Science Foundation","award":["L221013"],"award-info":[{"award-number":["L221013"]}]},{"name":"Youth Innovation Promotion Association CAS","award":["Y2021131"],"award-info":[{"award-number":["Y2021131"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681159","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"6453-6462","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single Sketch"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9463-2986","authenticated-orcid":false,"given":"Zidu","family":"Wang","sequence":"first","affiliation":[{"name":"MAIS, CASIA & School of Artificial Intelligence, UCAS, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4636-9677","authenticated-orcid":false,"given":"Xiangyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"MAIS, CASIA & School of Artificial Intelligence, UCAS, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3301-668X","authenticated-orcid":false,"given":"Jiang","family":"Yu","sequence":"additional","affiliation":[{"name":"Samsung Electronics (China) R&D Centre, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3199-9261","authenticated-orcid":false,"given":"Tianshuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"MAIS, CASIA & School of Artificial Intelligence, UCAS, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"MAIS, CASIA & School of Artificial Intelligence, UCAS, & CAIR, HKISI, CAS, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383165"},{"key":"e_1_3_2_1_2_1","volume-title":"ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling. arXiv preprint arXiv:2405.16570","author":"Babiloni Francesca","year":"2024","unstructured":"Francesca Babiloni, Alexandros Lattas, Jiankang Deng, and Stefanos Zafeiriou. 2024. ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling. arXiv preprint arXiv:2405.16570 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction. arXiv preprint arXiv:2211.13874","author":"Bai Haoran","year":"2022","unstructured":"Haoran Bai, Di Kang, Haoxian Zhang, Jinshan Pan, and Linchao Bao. 2022. FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction. arXiv preprint arXiv:2211.13874 (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"Tao Xiang, Ayan Kumar Bhunia, and Yi-Zhe Song.","author":"Bandyopadhyay Hmrishav","year":"2023","unstructured":"Hmrishav Bandyopadhyay, Subhadeep Koley, Ayan Das, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Ayan Kumar Bhunia, and Yi-Zhe Song. 2023. Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes. arXiv preprint arXiv:2312.04043 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Ananta R. Bhattarai Matthias Nie\u00dfner and Artem Sevastopolsky. 2024. TriPlaneNet: An Encoder for EG3D Inversion. (2024).","DOI":"10.1109\/WACV57701.2024.00303"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1227983"},{"key":"e_1_3_2_1_8_1","first-page":"120","article-title":"a. The openCV library","volume":"25","author":"Bradski Gary","year":"2000","unstructured":"Gary Bradski. 2000 a. The openCV library. Dr. Dobb's Journal: Software Tools for the Professional Programmer, Vol. 25, 11 (2000), 120--123.","journal-title":"Dr. Dobb's Journal: Software Tools for the Professional Programmer"},{"key":"e_1_3_2_1_9_1","first-page":"120","article-title":"b. The openCV library","volume":"25","author":"Bradski Gary","year":"2000","unstructured":"Gary Bradski. 2000 b. The openCV library. Dr. Dobb's Journal: Software Tools for the Professional Programmer, Vol. 25, 11 (2000), 120--123.","journal-title":"Dr. Dobb's Journal: Software Tools for the Professional Programmer"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1109\/TVCG.2013.249","article-title":"Facewarehouse: A 3d facial expression database for visual computing","volume":"20","author":"Cao Chen","year":"2013","unstructured":"Chen Cao, Yanlin Weng, Shun Zhou, Yiying Tong, and Kun Zhou. 2013. Facewarehouse: A 3d facial expression database for visual computing. IEEE Transactions on Visualization and Computer Graphics, Vol. 20, 3 (2013), 413--425.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_2_1_11_1","volume-title":"REALY: Rethinking the Evaluation of 3D Face Reconstruction. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27","author":"Chai Zenghao","year":"2022","unstructured":"Zenghao Chai, Haoxian Zhang, Jing Ren, Di Kang, Zhengzhuo Xu, Xuefei Zhe, Chun Yuan, and Linchao Bao. 2022. REALY: Rethinking the Evaluation of 3D Face Reconstruction. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part VIII. Springer, 74--92."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00834"},{"key":"e_1_3_2_1_13_1","volume-title":"Tao Xiang, Ayan Kumar Bhunia, and Yi-Zhe Song.","author":"Chen Dar-Yen","year":"2023","unstructured":"Dar-Yen Chen, Subhadeep Koley, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Ayan Kumar Bhunia, and Yi-Zhe Song. 2023. DemoCaricature: Democratising Caricature Generation with a Rough Sketch. (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Deepfaceediting: Deep face generation and editing with disentangled geometry and appearance control. arXiv preprint arXiv:2105.08935","author":"Chen Shu-Yu","year":"2021","unstructured":"Shu-Yu Chen, Feng-Lin Liu, Yu-Kun Lai, Paul L Rosin, Chunpeng Li, Hongbo Fu, and Lin Gao. 2021. Deepfaceediting: Deep face generation and editing with disentangled geometry and appearance control. arXiv preprint arXiv:2105.08935 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392386"},{"key":"e_1_3_2_1_16_1","volume-title":"Learning to predict 3d objects with an interpolation-based differentiable renderer. Advances in neural information processing systems","author":"Chen Wenzheng","year":"2019","unstructured":"Wenzheng Chen, Huan Ling, Jun Gao, Edward Smith, Jaakko Lehtinen, Alec Jacobson, and Sanja Fidler. 2019. Learning to predict 3d objects with an interpolation-based differentiable renderer. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_17_1","volume-title":"Generative adversarial networks: An overview","author":"Creswell Antonia","year":"2018","unstructured":"Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sengupta, and Anil A Bharath. 2018. Generative adversarial networks: An overview. IEEE signal processing magazine, Vol. 35, 1 (2018), 53--65."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01260-7"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"e_1_3_2_1_20_1","volume-title":"Emeline Got, Trevor Anderson, Amin Fadaeinejad, Rafael MO Cruz, and Marc-Andre Carbonneau.","author":"Dib Abdallah","year":"2023","unstructured":"Abdallah Dib, Luiz Gustavo Hafemann, Emeline Got, Trevor Anderson, Amin Fadaeinejad, Rafael MO Cruz, and Marc-Andre Carbonneau. 2023. MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading. arXiv preprint arXiv:2312.13091 (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_33"},{"key":"e_1_3_2_1_23_1","unstructured":"Clement Fuji Tsang Maria Shugrina Jean Francois Lafleche Towaki Takikawa Jiehan Wang Charles Loop Wenzheng Chen Krishna Murthy Jatavallabhula Edward Smith Artem Rozantsev Or Perel Tianchang Shen Jun Gao Sanja Fidler Gavriel State Jason Gorski Tommy Xiang Jianing Li Michael Li and Rev Lebaredian. 2022. Kaolin: A Pytorch Library for Accelerating 3D Deep Learning Research. https:\/\/github.com\/NVIDIAGameWorks\/kaolin."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_27"},{"key":"e_1_3_2_1_25_1","volume-title":"SketchFaceNeRF: Sketch-Based Facial Generation and Editing in Neural Radiance Fields. ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH 2023","volume":"42","author":"Gao Lin","year":"2023","unstructured":"Lin Gao, Feng-Lin Liu, Shu-Yu Chen, Kaiwen Jiang, Chun-Peng Li, Yu-Kun Lai, and Hongbo Fu. 2023. SketchFaceNeRF: Sketch-Based Facial Generation and Editing in Neural Radiance Fields. ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH 2023), Vol. 42, 4 (2023), 159:1--159:17."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00125"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01278"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Jianzhu Guo Xiangyu Zhu Yang Yang Fan Yang Zhen Lei and Stan Z Li. 2020. Towards fast accurate and stable 3d dense face alignment. (2020) 152--168.","DOI":"10.1007\/978-3-030-58529-7_10"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Yudong Guo Jianfei Cai Boyi Jiang Jianmin Zheng et al. 2018. Cnn-based real-time dense face reconstruction with inverse-rendered photo-realistic face images. IEEE transactions on pattern analysis and machine intelligence Vol. 41 6 (2018) 1294--1307.","DOI":"10.1109\/TPAMI.2018.2837742"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073629"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275535"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_35_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00084"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00834"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00046"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1131-1"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2868382"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413684"},{"key":"e_1_3_2_1_43_1","first-page":"1","article-title":"Face shape transfer via semantic warping","volume":"12","author":"Li Zonglin","year":"2024","unstructured":"Zonglin Li, Xiaoqian Lv, Wei Yu, Qinglin Liu, Jingbo Lin, and Shengping Zhang. 2024. Face shape transfer via semantic warping. Visual Intelligence, Vol. 12 (2024), 1--12.","journal-title":"Visual Intelligence"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00780"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00850"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02027"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul P. Srinivasan Matthew Tancik Jonathan T. Barron Ravi Ramamoorthi and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_3_2_1_50_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Pascal Paysan Reinhard Knothe Brian Amberg Sami Romdhani and Thomas Vetter. 2009. A 3D face model for pose and illumination invariant face recognition. In 2009 sixth IEEE international conference on advanced video and signal based surveillance. Ieee 296--301.","DOI":"10.1109\/AVSS.2009.58"},{"key":"e_1_3_2_1_52_1","volume-title":"Visual Intelligence","volume":"12","author":"Peng Siran","year":"2024","unstructured":"Siran Peng, Xiangyu Zhu, Dong Yi, Chen Qian, and Zhen Lei. 2024. Formulating facial mesh tracking as a differentiable optimization problem: a backpropagation-based solution. Visual Intelligence, Vol. 12 (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_3_2_1_54_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383317"},{"key":"e_1_3_2_1_56_1","volume-title":"Accelerating 3D Deep Learning with PyTorch3D. arXiv:2007.08501","author":"Ravi Nikhila","year":"2020","unstructured":"Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, and Georgia Gkioxari. 2020. Accelerating 3D Deep Learning with PyTorch3D. arXiv:2007.08501 (2020)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.59"},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings, Part XV. Springer, 53--70","author":"Shang Jiaxiang","year":"2020","unstructured":"Jiaxiang Shang, Tianwei Shen, Shiwei Li, Lei Zhou, Mingmin Zhen, Tian Fang, and Long Quan. 2020. Self-supervised monocular 3d face reconstruction by occlusion-aware multi-view geometry consistency. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XV. Springer, 53--70."},{"key":"e_1_3_2_1_60_1","volume-title":"Bill The Khronos OpenGL ARB Working Group, et al","author":"Shreiner Dave","year":"2009","unstructured":"Dave Shreiner, Bill The Khronos OpenGL ARB Working Group, et al. 2009. OpenGL programming guide: the official guide to learning OpenGL, versions 3.0 and 3.1. Pearson Education."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3132703","article-title":"Mastering sketching: adversarial augmentation for structured prediction","volume":"37","author":"Simo-Serra Edgar","year":"2018","unstructured":"Edgar Simo-Serra, Satoshi Iizuka, and Hiroshi Ishikawa. 2018. Mastering sketching: adversarial augmentation for structured prediction. ACM Transactions on Graphics (TOG), Vol. 37, 1 (2018), 1--13.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925972"},{"key":"e_1_3_2_1_63_1","volume-title":"HeadEvolver: Text to Head Avatars via Locally Learnable Mesh Deformation. arXiv preprint arXiv:2403.09326","author":"Wang Duotun","year":"2024","unstructured":"Duotun Wang, Hengyu Meng, Zeyu Cai, Zhijing Shao, Qianxi Liu, Lin Wang, Mingming Fan, Ying Shan, Xiaohang Zhan, and Zeyu Wang. 2024. HeadEvolver: Text to Head Avatars via Locally Learnable Mesh Deformation. arXiv preprint arXiv:2403.09326 (2024)."},{"key":"e_1_3_2_1_64_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_65_1","volume-title":"3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation. arXiv preprint arXiv:2312.00311","author":"Wang Zidu","year":"2023","unstructured":"Zidu Wang, Xiangyu Zhu, Tianshuo Zhang, Baiqin Wang, and Zhen Lei. 2023. 3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation. arXiv preprint arXiv:2312.00311 (2023)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3391888"},{"key":"e_1_3_2_1_67_1","volume-title":"Deep learning for free-hand sketch: A survey","author":"Xu Peng","year":"2022","unstructured":"Peng Xu, Timothy M Hospedales, Qiyue Yin, Yi-Zhe Song, Tao Xiang, and Liang Wang. 2022. Deep learning for free-hand sketch: A survey. IEEE transactions on pattern analysis and machine intelligence, Vol. 45, 1 (2022), 285--312."},{"key":"e_1_3_2_1_68_1","volume-title":"Dialoguenerf: Towards realistic avatar face-to-face conversation video generation. arXiv preprint arXiv:2203.07931","author":"Yan Yichao","year":"2022","unstructured":"Yichao Yan, Zanwei Zhou, Zi Wang, Jingnan Gao, and Xiaokang Yang. 2022. Dialoguenerf: Towards realistic avatar face-to-face conversation video generation. arXiv preprint arXiv:2203.07931 (2022)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gmod.2021.101102"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00595"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Qi Zheng Jiankang Deng Zheng Zhu Ying Li and Stefanos Zafeiriou. 2022. Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing. In Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR52688.2022.00412"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592103","article-title":"Locally attentional sdf diffusion for controllable 3d shape generation","volume":"42","author":"Zheng Xin-Yang","year":"2023","unstructured":"Xin-Yang Zheng, Hao Pan, Peng-Shuai Wang, Xin Tong, Yang Liu, and Heung-Yeung Shum. 2023. Locally attentional sdf diffusion for controllable 3d shape generation. ACM Transactions on Graphics (TOG), Vol. 42, 4 (2023), 1--13.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_74_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 787--796","author":"Zhu Xiangyu","year":"2015","unstructured":"Xiangyu Zhu, Zhen Lei, Junjie Yan, Dong Yi, and Stan Z Li. 2015. High-fidelity pose and expression normalization for face recognition in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition. 787--796."},{"key":"e_1_3_2_1_75_1","volume-title":"Face alignment in full pose range: A 3d total solution","author":"Zhu Xiangyu","year":"2017","unstructured":"Xiangyu Zhu, Xiaoming Liu, Zhen Lei, and Stan Z Li. 2017. Face alignment in full pose range: A 3d total solution. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 1 (2017), 78--92."},{"key":"e_1_3_2_1_76_1","volume-title":"Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape","author":"Zhu Xiangyu","year":"2022","unstructured":"Xiangyu Zhu, Chang Yu, Di Huang, Zhen Lei, Hao Wang, and Stan Z Li. 2022. Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681159","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":76,"alternative-id":["10.1145\/3664647.3681159","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681159","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}