{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:08Z","timestamp":1750309508853,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":66,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271405, 62171255"],"award-info":[{"award-number":["62271405, 62171255"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University - Migu Xinkong Culture Technology (Xiamen) Co.Ltd. Joint Research Center for Intelligent Light Field and Interaction Technology"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680607","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"6793-6802","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DisControlFace: Adding Disentangled Control to Diffusion Autoencoder for One-shot Explicit Facial Image Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1224-354X","authenticated-orcid":false,"given":"Haozhe","family":"Jia","sequence":"first","affiliation":[{"name":"Huawei Technologies Co., Ltd, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1331-9182","authenticated-orcid":false,"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8625-2521","authenticated-orcid":false,"given":"Hengfei","family":"Cui","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5464-9858","authenticated-orcid":false,"given":"Di","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6880-959X","authenticated-orcid":false,"given":"Yuwang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3818-5069","authenticated-orcid":false,"given":"Tao","family":"Yu","sequence":"additional","affiliation":[{"name":"Tsinghua University, 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\/CVPRW59228.2023.00091"},{"key":"e_1_3_2_1_2_1","first-page":"19900","article-title":"Generative neural articulated radiance fields","volume":"35","author":"Bergman Alexander","year":"2022","unstructured":"Alexander Bergman, Petr Kellnhofer, Wang Yifan, Eric Chan, David Lindell, and Gordon Wetzstein. 2022. Generative neural articulated radiance fields. Advances in Neural Information Processing Systems (NeurIPS), Vol. 35 (2022), 19900--19916.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596730"},{"key":"e_1_3_2_1_4_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 (TVCG), Vol. 20, 3 (2013), 413--425.","journal-title":"IEEE Transactions on Visualization and Computer Graphics (TVCG)"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20311--20322","author":"Danvevcek Radek","year":"2022","unstructured":"Radek Danvevcek, Michael J Black, and Timo Bolkart. 2022. EMOCA: Emotion driven monocular face capture and animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20311--20322."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00520"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01041"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01258"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01225"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459936","article-title":"Learning an animatable detailed 3D face model from in-the-wild images","volume":"40","author":"Feng Yao","year":"2021","unstructured":"Yao Feng, Haiwen Feng, Michael J Black, and Timo Bolkart. 2021. Learning an animatable detailed 3D face model from in-the-wild images. ACM Transactions on Graphics (ToG), Vol. 40, 4 (2021), 1--13.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00021"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00097"},{"key":"e_1_3_2_1_18_1","volume-title":"Stylenerf: A style-based 3d-aware generator for high-resolution image synthesis. arXiv preprint arXiv:2110.08985","author":"Gu Jiatao","year":"2021","unstructured":"Jiatao Gu, Lingjie Liu, Peng Wang, and Christian Theobalt. 2021. Stylenerf: A style-based 3d-aware generator for high-resolution image synthesis. arXiv preprint arXiv:2110.08985 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSIAI.2010.5483908"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_21_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","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 (NeurIPS), Vol. 33. 6840--6851.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR).","author":"Hong Fangzhou","year":"2022","unstructured":"Fangzhou Hong, Zhaoxi Chen, LAN Yushi, Liang Pan, and Ziwei Liu. 2022. EVA3D: Compositional 3D Human Generation from 2D Image Collections. In Proceedings of the Eleventh International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20374--20384","author":"Hong Yang","year":"2022","unstructured":"Yang Hong, Bo Peng, Haiyao Xiao, Ligang Liu, and Juyong Zhang. 2022. Headnerf: A real-time nerf-based parametric head model. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20374--20384."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=Hk99zCeAb","author":"Karras Tero","year":"2018","unstructured":"Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2018. Progressive Growing of GANs for Improved Quality, Stability, and Variation. In Proceedings of the International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=Hk99zCeAb"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00046"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_2_1_30_1","first-page":"1","article-title":"Neural actor: Neural free-view synthesis of human actors with pose control","volume":"40","author":"Liu Lingjie","year":"2021","unstructured":"Lingjie Liu, Marc Habermann, Viktor Rudnev, Kripasindhu Sarkar, Jiatao Gu, and Christian Theobalt. 2021. Neural actor: Neural free-view synthesis of human actors with pose control. ACM Transactions on Graphics (TOG), Vol. 40, 6 (2021), 1--16.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_7"},{"key":"e_1_3_2_1_32_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 7588--7597","author":"Nguyen-Phuoc Thu","year":"2019","unstructured":"Thu Nguyen-Phuoc, Chuan Li, Lucas Theis, Christian Richardt, and Yong-Liang Yang. 2019. Hologan: Unsupervised learning of 3d representations from natural images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 7588--7597."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555436"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_36"},{"key":"e_1_3_2_1_38_1","first-page":"20002","article-title":"A shading-guided generative implicit model for shape-accurate 3d-aware image synthesis","volume":"34","author":"Pan Xingang","year":"2021","unstructured":"Xingang Pan, Xudong Xu, Chen Change Loy, Christian Theobalt, and Bo Dai. 2021. A shading-guided generative implicit model for shape-accurate 3d-aware image synthesis. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 34. 20002--20013.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_31"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02070"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_46_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI)","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, 234--241."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_48_1","first-page":"4713","article-title":"Image super-resolution via iterative refinement","volume":"45","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J Fleet, and Mohammad Norouzi. 2022. Image super-resolution via iterative refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 45, 4 (2022), 4713--4726.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)"},{"key":"e_1_3_2_1_49_1","first-page":"20154","article-title":"Graf: Generative radiance fields for 3d-aware image synthesis","volume":"33","author":"Schwarz Katja","year":"2020","unstructured":"Katja Schwarz, Yiyi Liao, Michael Niemeyer, and Andreas Geiger. 2020. Graf: Generative radiance fields for 3d-aware image synthesis. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 33. 20154--20166.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.175"},{"volume-title":"Advances in neural information processing systems (NeurIPS)","author":"Sitzmann Vincent","key":"e_1_3_2_1_51_1","unstructured":"Vincent Sitzmann, Julien Martel, Alexander Bergman, David Lindell, and Gordon Wetzstein. 2020. Implicit neural representations with periodic activation functions. In Advances in neural information processing systems (NeurIPS), Vol. 33. 7462--7473."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00254"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising Diffusion Implicit Models. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02011"},{"key":"e_1_3_2_1_55_1","first-page":"16331","article-title":"Controllable 3d face synthesis with conditional generative occupancy fields","volume":"35","author":"Sun Keqiang","year":"2022","unstructured":"Keqiang Sun, Shangzhe Wu, Zhaoyang Huang, Ning Zhang, Quan Wang, and Hongsheng Li. 2022. Controllable 3d face synthesis with conditional generative occupancy fields. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 35. 16331--16343.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01107"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 3361--3371","author":"Tewari Ayush","year":"2021","unstructured":"Ayush Tewari, Hans-Peter Seidel, Mohamed Elgharib, Christian Theobalt, et al. 2021. Learning complete 3d morphable face models from images and videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 3361--3371."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00122"},{"key":"e_1_3_2_1_59_1","first-page":"157","article-title":"On learning 3d face morphable model from in-the-wild images","volume":"43","author":"Tran Luan","year":"2019","unstructured":"Luan Tran and Xiaoming Liu. 2019. On learning 3d face morphable model from in-the-wild images. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 43, 1 (2019), 157--171.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"e_1_3_2_1_60_1","volume-title":"Face0: Instantaneously Conditioning a Text-to-Image Model on a Face. arXiv preprint arXiv:2306.06638","author":"Valevski Dani","year":"2023","unstructured":"Dani Valevski, Danny Wasserman, Yossi Matias, and Yaniv Leviathan. 2023. Face0: Instantaneously Conditioning a Text-to-Image Model on a Face. arXiv preprint arXiv:2306.06638 (2023)."},{"key":"e_1_3_2_1_61_1","volume-title":"DisCo: Disentangled Control for Referring Human Dance Generation in Real World. arXiv preprint arXiv:2307.00040","author":"Wang Tan","year":"2023","unstructured":"Tan Wang, Linjie Li, Kevin Lin, Chung-Ching Lin, Zhengyuan Yang, Hanwang Zhang, Zicheng Liu, and Lijuan Wang. 2023. DisCo: Disentangled Control for Referring Human Dance Generation in Real World. arXiv preprint arXiv:2307.00040 (2023)."},{"key":"e_1_3_2_1_62_1","first-page":"36188","article-title":"Anifacegan: Animatable 3d-aware face image generation for video avatars","volume":"35","author":"Wu Yue","year":"2022","unstructured":"Yue Wu, Yu Deng, Jiaolong Yang, Fangyun Wei, Qifeng Chen, and Xin Tong. 2022. Anifacegan: Animatable 3d-aware face image generation for video avatars. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 35. 36188--36201.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00068"},{"key":"e_1_3_2_1_64_1","volume-title":"Inserting Anybody in Diffusion Models via Celeb Basis. arXiv preprint arXiv:2306.00926","author":"Yuan Ge","year":"2023","unstructured":"Ge Yuan, Xiaodong Cun, Yong Zhang, Maomao Li, Chenyang Qi, Xintao Wang, Ying Shan, and Huicheng Zheng. 2023. Inserting Anybody in Diffusion Models via Celeb Basis. arXiv preprint arXiv:2306.00926 (2023)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_66_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13545--13555","author":"Zheng Yufeng","year":"2022","unstructured":"Yufeng Zheng, Victoria Fern\u00e1ndez Abrevaya, Marcel C B\u00fchler, Xu Chen, Michael J Black, and Otmar Hilliges. 2022. Im avatar: Implicit morphable head avatars from videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13545--13555."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680607","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680607"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":66,"alternative-id":["10.1145\/3664647.3680607","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680607","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"}}]}}