{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:37:51Z","timestamp":1769632671423,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":113,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441224, 62272433"],"award-info":[{"award-number":["62441224, 62272433"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["WK0010000090"],"award-info":[{"award-number":["WK0010000090"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763953","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:27:29Z","timestamp":1765211249000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Constructing Diffusion Avatar with Learnable Embeddings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9396-0761","authenticated-orcid":false,"given":"Xuan","family":"Gao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0518-3885","authenticated-orcid":false,"given":"Jingtao","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3189-405X","authenticated-orcid":false,"given":"Dongyu","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5656-8475","authenticated-orcid":false,"given":"Yuqi","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1805-1426","authenticated-orcid":false,"given":"Juyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China and Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687580"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Chen Cao Tomas Simon Jin\u00a0Kyu Kim Gabe Schwartz Michael Zollhoefer Shun-Suke Saito Stephen Lombardi Shih-En Wei Danielle Belko Shoou-I Yu et\u00a0al. 2022. Authentic volumetric avatars from a phone scan. ACM Transactions on Graphics (TOG) 41 4 (2022) 1\u201319.","DOI":"10.1145\/3528223.3530143"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","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 20 3 (2013) 413\u2013425.","DOI":"10.1109\/TVCG.2013.249"},{"key":"e_1_3_3_2_8_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024","author":"Chang Di","year":"2024","unstructured":"Di Chang, Yichun Shi, Quankai Gao, Hongyi Xu, Jessica Fu, Guoxian Song, Qing Yan, Yizhe Zhu, Xiao Yang, and Mohammad Soleymani. 2024. MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00986"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1838"},{"key":"e_1_3_3_2_11_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chu Xuangeng","year":"2024","unstructured":"Xuangeng Chu, Yu Li, Ailing Zeng, Tianyu Yang, Lijian Lin, Yunfei Liu, and Tatsuya Harada. 2024. GPAvatar: Generalizable and Precise Head Avatar from Image(s). In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126510"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00680"},{"key":"e_1_3_3_2_15_1","volume-title":"ECCV","author":"Deng Yu","year":"2024","unstructured":"Yu Deng, Duomin Wang, and baoyuan Wang. 2024a. Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer. In ECCV."},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00812"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547838"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Dimitrios Gerogiannis Foivos\u00a0Paraperas Papantoniou Rolandos\u00a0Alexandros Potamias Alexandros Lattas and Stefanos Zafeiriou. 2025. Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.05379 (2025).","DOI":"10.1109\/CVPR52734.2025.01006"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00097"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02012"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00995"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687571"},{"key":"e_1_3_3_2_23_1","unstructured":"Jianzhu Guo Dingyun Zhang Xiaoqiang Liu Zhizhou Zhong Yuan Zhang Pengfei Wan and Di Zhang. 2024. LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.03168 (2024)."},{"key":"e_1_3_3_2_24_1","first-page":"20","volume-title":"European Conference on Computer Vision","author":"Han Yue","year":"2024","unstructured":"Yue Han, Junwei Zhu, Keke He, Xu Chen, Yanhao Ge, Wei Li, Xiangtai Li, Jiangning Zhang, Chengjie Wang, and Yong Liu. 2024. Face-Adapter for Pre-trained Diffusion Models with Fine-Grained ID and Attribute Control. In European Conference on Computer Vision. Springer, 20\u201336."},{"key":"e_1_3_3_2_25_1","unstructured":"Xu He Xiaoyu Li Di Kang Jiangnan Ye Chaopeng Zhang Liyang Chen Xiangjun Gao Han Zhang Zhiyong Wu and Haolin Zhuang. 2024. Magicman: Generative novel view synthesis of humans with 3d-aware diffusion and iterative refinement. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.14211 (2024)."},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00058"},{"key":"e_1_3_3_2_27_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02108"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"e_1_3_3_2_30_1","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hong Yang","year":"2022","unstructured":"Yang Hong, Bo Peng, Haiyao Xiao, Ligang Liu, and Juyong Zhang. 2022a. HeadNeRF: A Real-time NeRF-based Parametric Head Model. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_31_1","first-page":"8153","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu Li","year":"2024","unstructured":"Li Hu. 2024. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8153\u20138163."},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Yash Kant Ethan Weber Jin\u00a0Kyu Kim Rawal Khirodkar Su Zhaoen Julieta Martinez Igor Gilitschenski Shunsuke Saito and Timur Bagautdinov. 2025. Pippo: High-Resolution Multi-View Humans from a Single Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.07785 (2025).","DOI":"10.1109\/CVPR52734.2025.01531"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics 42 4 (July 2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_20"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00524"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","unstructured":"Tobias Kirschstein Shenhan Qian Simon Giebenhain Tim Walter and Matthias Nie\u00dfner. 2023. NeRSemble: Multi-View Radiance Field Reconstruction of Human Heads. ACM Trans. Graph. 42 4 Article 161 (jul 2023) 14\u00a0pages. 10.1145\/3592455","DOI":"10.1145\/3592455"},{"key":"e_1_3_3_2_37_1","volume-title":"ECCV","author":"Lan Yushi","year":"2024","unstructured":"Yushi Lan, Feitong Tan, Di Qiu, Qiangeng Xu, Kyle Genova, Zeng Huang, Sean Fanello, Rohit Pandey, Thomas Funkhouser, Chen\u00a0Change Loy, and Yinda Zhang. 2024. Gaussian3Diff: 3D Gaussian Diffusion for 3D Full Head Synthesis and Editing. In ECCV."},{"key":"e_1_3_3_2_38_1","first-page":"324","volume-title":"European Conference on Computer Vision","author":"Li Heyuan","year":"2024","unstructured":"Heyuan Li, Ce Chen, Tianhao Shi, Yuda Qiu, Sizhe An, Guanying Chen, and Xiaoguang Han. 2024a. Spherehead: stable 3d full-head synthesis with spherical tri-plane representation. In European Conference on Computer Vision. Springer, 324\u2013341."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"crossref","unstructured":"Tianye Li Timo Bolkart Michael\u00a0J Black Hao Li and Javier Romero. 2017a. Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. 36 6 (2017) 194\u20131.","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","unstructured":"Tianye Li Timo Bolkart Michael.\u00a0J. Black Hao Li and Javier Romero. 2017b. Learning a model of facial shape and expression from 4D scans. ACM Transactions on Graphics (Proc. SIGGRAPH Asia) 36 6 (2017) 194:1\u2013194:17. https:\/\/doi.org\/10.1145\/3130800.3130813","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01723"},{"key":"e_1_3_3_2_42_1","unstructured":"Xueting Li Shalini De\u00a0Mello Sifei Liu Koki Nagano Umar Iqbal and Jan Kautz. 2023a. Generalizable One-shot Neural Head Avatar. NeurIPS (2023)."},{"key":"e_1_3_3_2_43_1","unstructured":"Xueting Li Shalini De\u00a0Mello Sifei Liu Koki Nagano Umar Iqbal and Jan Kautz. 2024b. Generalizable one-shot 3D neural head avatar. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_44_1","unstructured":"Yixing Lu Junting Dong Youngjoong Kwon Qin Zhao Bo Dai and Fernando De\u00a0la Torre. 2025. GAS: Generative Avatar Synthesis from a Single Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.06957 (2025)."},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01621"},{"key":"e_1_3_3_2_47_1","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Mallya Arun","year":"2022","unstructured":"Arun Mallya, Ting-Chun Wang, and Ming-Yu Liu. 2022. Implicit Warping for Animation with Image Sets. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"crossref","unstructured":"Mohit Mendiratta Xingang Pan Mohamed Elgharib Kartik Teotia Mallikarjun\u00a0B R Ayush Tewari Vladislav Golyanik Adam Kortylewski and Christian Theobalt. 2023. AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars. arxiv:https:\/\/arXiv.org\/abs\/2306.00547\u00a0[cs.CV]","DOI":"10.1145\/3618368"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_2_50_1","series-title":"(LNCS)","volume-title":"European Conference on Computer Vision (ECCV 2024)","author":"Ostrek Mirela","year":"2024","unstructured":"Mirela Ostrek and Justus Thies. 2024. Stable Video Portraits. In European Conference on Computer Vision (ECCV 2024)(LNCS). Springer Cham. https:\/\/svp.is.tue.mpg.de\/"},{"key":"e_1_3_3_2_51_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Pan Dongwei","year":"2023","unstructured":"Dongwei Pan, Long Zhuo, Jingtan Piao, Huiwen Luo, Wei Cheng, Yuxin Wang, Siming Fan, Shengqi Liu, Lei Yang, Bo Dai, Ziwei Liu, Chen\u00a0Change Loy, Chen Qian, Wayne Wu, Dahua Lin, and Kwan-Yee Lin. 2023. RenderMe-360: Large Digital Asset Library and Benchmark Towards High-fidelity Head Avatars. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_3_2_52_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Paraperas\u00a0Papantoniou Foivos","year":"2024","unstructured":"Foivos Paraperas\u00a0Papantoniou, Alexandros Lattas, Stylianos Moschoglou, Jiankang Deng, Bernhard Kainz, and Stefanos Zafeiriou. 2024. Arc2Face: A Foundation Model for ID-Consistent Human Faces. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00148"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00241"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00021"},{"key":"e_1_3_3_2_59_1","volume-title":"International Conference on Learning Representations","author":"Salimans Tim","year":"2022","unstructured":"Tim Salimans and Jonathan Ho. 2022. Progressive Distillation for Fast Sampling of Diffusion Models. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_60_1","unstructured":"Jack Saunders Charlie Hewitt Yanan Jian Marek Kowalski Tadas Baltru\u0161aitis Yiye Chen Darren Cosker Virginia Estellers Nicholas Gyde Vinay\u00a0P. Namboodiri and Benjamin\u00a0E Lundell. 2024. GASP: Gaussian Avatars with Synthetic Priors. arxiv:https:\/\/arXiv.org\/abs\/2412.07739\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2412.07739"},{"key":"e_1_3_3_2_61_1","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Siarohin Aliaksandr","year":"2019","unstructured":"Aliaksandr Siarohin, St\u00e9phane Lathuili\u00e8re, Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019. First Order Motion Model for Image Animation. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"e_1_3_3_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02011"},{"key":"e_1_3_3_2_64_1","unstructured":"Jiapeng Tang Davide Davoli Tobias Kirschstein Liam Schoneveld and Matthias Niessner. 2024. GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.10209 (2024)."},{"key":"e_1_3_3_2_65_1","doi-asserted-by":"crossref","unstructured":"Felix Taubner Ruihang Zhang Mathieu Tuli and David\u00a0B. Lindell. 2024. CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models. (2024).","DOI":"10.1109\/CVPR52734.2025.00501"},{"key":"e_1_3_3_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00618"},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"crossref","unstructured":"Justus Thies Michael Zollh\u00f6fer and Matthias Nie\u00dfner. 2019. Deferred neural rendering: Image synthesis using neural textures. Acm Transactions on Graphics (TOG) 38 4 (2019) 1\u201312.","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_3_3_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00767"},{"key":"e_1_3_3_2_69_1","doi-asserted-by":"crossref","unstructured":"Phong Tran Egor Zakharov Long-Nhat Ho Liwen Hu Adilbek Karmanov Aviral Agarwal McLean Goldwhite Ariana\u00a0Bermudez Venegas Anh\u00a0Tuan Tran and Hao Li. 2024a. VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.16204 (2024).","DOI":"10.1145\/3687974"},{"key":"e_1_3_3_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00984"},{"key":"e_1_3_3_2_71_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141\u00a0ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems , I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_3_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"e_1_3_3_2_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"e_1_3_3_2_74_1","unstructured":"Qixun Wang Xu Bai Haofan Wang Zekui Qin and Anthony Chen. 2024. Instantid: Zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.07519 (2024)."},{"key":"e_1_3_3_2_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"e_1_3_3_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_3_2_77_1","unstructured":"Huawei Wei Zejun Yang and Zhisheng Wang. 2024. AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animations. arxiv:https:\/\/arXiv.org\/abs\/2403.17694\u00a0[cs.CV]"},{"key":"e_1_3_3_2_78_1","volume-title":"Advances in Neural Information Processing Systems","author":"Wu Yue","year":"2022","unstructured":"Yue Wu, Yu Deng, Jiaolong Yang, Fangyun Wei, Chen Qifeng, and Xin Tong. 2022. AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_2_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618164"},{"key":"e_1_3_3_2_80_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2207.11243"},{"key":"e_1_3_3_2_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00177"},{"key":"e_1_3_3_2_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00081"},{"key":"e_1_3_3_2_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"e_1_3_3_2_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"e_1_3_3_2_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00773"},{"key":"e_1_3_3_2_86_1","unstructured":"Yuelang Xu Benwang Chen Zhe Li Hongwen Zhang Lizhen Wang Zerong Zheng and Yebin Liu. 2023. Gaussian head avatar: Ultra high-fidelity head avatar via dynamic gaussians. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.03029 (2023)."},{"key":"e_1_3_3_2_87_1","first-page":"129","volume-title":"European Conference on Computer Vision","author":"Xu Yuelang","year":"2024","unstructured":"Yuelang Xu, Lizhen Wang, Zerong Zheng, Zhaoqi Su, and Yebin Liu. 2024b. 3d gaussian parametric head model. In European Conference on Computer Vision. Springer, 129\u2013147."},{"key":"e_1_3_3_2_88_1","unstructured":"Ziyi Xu Ziyao Huang Juan Cao Yong Zhang Xiaodong Cun Qing Shuai Yuchen Wang Linchao Bao Jintao Li and Fan Tang. 2024a. AnchorCrafter: Animate CyberAnchors Saling Your Products via Human-Object Interacting Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.17383 (2024)."},{"key":"e_1_3_3_2_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"e_1_3_3_2_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680619"},{"key":"e_1_3_3_2_91_1","doi-asserted-by":"crossref","unstructured":"Quanwei Yang Jiazhi Guan Kaisiyuan Wang Lingyun Yu Wenqing Chu Hang Zhou ZhiQiang Feng Haocheng Feng Errui Ding Jingdong Wang et\u00a0al. 2025. Showmaker: Creating high-fidelity 2d human video via fine-grained diffusion modeling. Advances in Neural Information Processing Systems 37 (2025) 51039\u201351062.","DOI":"10.52202\/079017-1615"},{"key":"e_1_3_3_2_92_1","unstructured":"Shurong Yang Huadong Li Juhao Wu Minhao Jing Linze Li Renhe Ji Jiajun Liang and Haoqiang Fan. 2024a. MegActor: Harness the Power of Raw Video for Vivid Portrait Animation. arxiv:https:\/\/arXiv.org\/abs\/2405.20851\u00a0[cs.CV]"},{"key":"e_1_3_3_2_93_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Ye Zhenhui","year":"2024","unstructured":"Zhenhui Ye, Tianyun Zhong, Yi Ren, Jiaqi Yang, Weichuang Li, Jiawei Huang, Ziyue Jiang, Jinzheng He, Rongjie Huang, Jinglin Liu, Chen Zhang, Xiang Yin, Zejun Ma, and Zhou Zhao. 2024. Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024."},{"key":"e_1_3_3_2_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01261"},{"key":"e_1_3_3_2_95_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"e_1_3_3_2_96_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591555"},{"key":"e_1_3_3_2_97_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00306"},{"key":"e_1_3_3_2_98_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"e_1_3_3_2_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00070"},{"key":"e_1_3_3_2_100_1","first-page":"465","volume-title":"European Conference on Computer Vision","author":"Zhang Bowen","year":"2024","unstructured":"Bowen Zhang, Yiji Cheng, Chunyu Wang, Ting Zhang, Jiaolong Yang, Yansong Tang, Feng Zhao, Dong Chen, and Baining Guo. 2024. Rodinhd: High-fidelity 3d avatar generation with diffusion models. In European Conference on Computer Vision. Springer, 465\u2013483."},{"key":"e_1_3_3_2_101_1","doi-asserted-by":"publisher","unstructured":"Longwen Zhang Qiwei Qiu Hongyang Lin Qixuan Zhang Cheng Shi Wei Yang Ye Shi Sibei Yang Lan Xu and Jingyi Yu. 2023b. DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance. ACM Trans. Graph. 42 4 (2023) 138:1\u2013138:16. 10.1145\/3592094","DOI":"10.1145\/3592094"},{"key":"e_1_3_3_2_102_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_103_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"e_1_3_3_2_104_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"e_1_3_3_2_105_1","doi-asserted-by":"crossref","unstructured":"Wenliang Zhao Yongming Rao Weikang Shi Zuyan Liu Jie Zhou and Jiwen Lu. 2023. DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion. CVPR (2023).","DOI":"10.1109\/CVPR52729.2023.00828"},{"key":"e_1_3_3_2_106_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01970"},{"key":"e_1_3_3_2_107_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Cecilia\u00a0Zhang Zhihao Xia Lars Jebe Zhuowen\u00a0Tu Zheng\u00a0Ding,","year":"2023","unstructured":"Zhihao Xia Lars Jebe Zhuowen\u00a0Tu Zheng\u00a0Ding, Cecilia\u00a0Zhang and Xiuming Zhang. 2023. DiffusionRig: Learning Personalized Priors for Facial Appearance Editing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_3_2_108_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"e_1_3_3_2_109_1","unstructured":"Jingkai Zhou Benzhi Wang Weihua Chen Jingqi Bai Dongyang Li Aixi Zhang Hao Xu Mingyang Yang and Fan Wang. 2024. RealisDance: Equip controllable character animation with realistic hands. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.06202 (2024)."},{"key":"e_1_3_3_2_110_1","doi-asserted-by":"crossref","unstructured":"Hao Zhu Haotian Yang Longwei Guo Yidi Zhang Yanru Wang Mingkai Huang Menghua Wu Qiu Shen Ruigang Yang and Xun Cao. 2023. FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2023).","DOI":"10.1109\/TPAMI.2023.3307338"},{"key":"e_1_3_3_2_111_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Zhu Shenhao","year":"2024","unstructured":"Shenhao Zhu, Junming\u00a0Leo Chen, Zuozhuo Dai, Yinghui Xu, Xun Cao, Yao Yao, Hao Zhu, and Siyu Zhu. 2024. Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_112_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.23"},{"key":"e_1_3_3_2_113_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_16"},{"key":"e_1_3_3_2_114_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01003"}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:24:44Z","timestamp":1765250684000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763953"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":113,"alternative-id":["10.1145\/3757377.3763953","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763953","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}