{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T06:59:09Z","timestamp":1764053949952,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":61,"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":[{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"name":"NSFC","award":["62201342, 62101325"],"award-info":[{"award-number":["62201342, 62101325"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681409","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"6860-6869","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["<i>E<\/i>\n            <sup>3<\/sup>\n            Gen: Efficient, Expressive and Editable Avatars Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6760-1132","authenticated-orcid":false,"given":"Weitian","family":"Zhang","sequence":"first","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3209-8965","authenticated-orcid":false,"given":"Yichao","family":"Yan","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5718-2282","authenticated-orcid":false,"given":"Yunhui","family":"Liu","sequence":"additional","affiliation":[{"name":"Lenovo Research, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9980-1392","authenticated-orcid":false,"given":"Xingdong","family":"Sheng","sequence":"additional","affiliation":[{"name":"Lenovo Research, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Rameen Abdal Wang Yifan Zifan Shi Yinghao Xu Ryan Po Zhengfei Kuang Qifeng Chen Dit-Yan Yeung and Gordon Wetzstein. 2023. Gaussian Shell Maps for Efficient 3D Human Generation. arxiv: 2311.17857 [cs.CV]","DOI":"10.1109\/CVPR52733.2024.00902"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459850"},{"key":"e_1_3_2_1_3_1","unstructured":"Alexander W. Bergman Petr Kellnhofer Wang Yifan Eric R. Chan David B. Lindell and Gordon Wetzstein. 2022. Generative Neural Articulated Radiance Fields. In NeurIPS."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"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\/ICCV51070.2023.00229"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00825"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01978"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01139"},{"key":"e_1_3_2_1_10_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems.","author":"Chen Zhaoxi","year":"2023","unstructured":"Zhaoxi Chen, Fangzhou Hong, Haiyi Mei, Guangcong Wang, Lei Yang, and Ziwei Liu. 2023. PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings, Part XII 16","author":"Chu Hang","year":"2020","unstructured":"Hang Chu, Shugao Ma, Fernando De la Torre, Sanja Fidler, and Yaser Sheikh. 2020. Expressive telepresence via modular codec avatars. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XII 16. Springer, 330--345."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766945"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01170"},{"key":"e_1_3_2_1_14_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, Vol. 34 (2021), 8780--8794."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01370"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 14300--14310","author":"Erkocc Ziya","year":"2023","unstructured":"Ziya Erkocc, Fangchang Ma, Qi Shan, Matthias Nie\u00dfner, and Angela Dai. 2023. HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 14300--14310."},{"key":"e_1_3_2_1_17_1","first-page":"31841","article-title":"Get3d: A generative model of high quality 3d textured shapes learned from images","volume":"35","author":"Gao Jun","year":"2022","unstructured":"Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, and Sanja Fidler. 2022. Get3d: A generative model of high quality 3d textured shapes learned from images. Advances In Neural Information Processing Systems, Vol. 35 (2022), 31841--31854.","journal-title":"Advances In Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00511"},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=iUuzzTMUw9K","author":"Gu Jiatao","year":"2022","unstructured":"Jiatao Gu, Lingjie Liu, Peng Wang, and Christian Theobalt. 2022. StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=iUuzzTMUw9K"},{"key":"e_1_3_2_1_20_1","first-page":"1","article-title":"The relightables: Volumetric performance capture of humans with realistic relighting","volume":"38","author":"Guo Kaiwen","year":"2019","unstructured":"Kaiwen Guo, Peter Lincoln, Philip Davidson, Jay Busch, Xueming Yu, Matt Whalen, Geoff Harvey, Sergio Orts-Escolano, Rohit Pandey, Jason Dourgarian, et al. 2019. The relightables: Volumetric performance capture of humans with realistic relighting. ACM Transactions on Graphics (ToG), Vol. 38, 6 (2019), 1--19.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"e_1_3_2_1_21_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=g7U9jD_2CUr","author":"Hong Fangzhou","year":"2023","unstructured":"Fangzhou Hong, Zhaoxi Chen, Yushi LAN, Liang Pan, and Ziwei Liu. 2023. EVA3D: Compositional 3D Human Generation from 2D Image Collections. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=g7U9jD_2CUr"},{"key":"e_1_3_2_1_23_1","volume-title":"HumanLiff: Layer-wise 3D Human Generation with Diffusion Model. arXiv preprint","author":"Hu Shoukang","year":"2023","unstructured":"Shoukang Hu, Fangzhou Hong, Tao Hu, Liang Pan, Haiyi Mei, Weiye Xiao, Lei Yang, and Ziwei Liu. 2023. HumanLiff: Layer-wise 3D Human Generation with Diffusion Model. arXiv preprint (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. NeurIPS.","author":"Karras Tero","year":"2020","unstructured":"Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, and Timo Aila. 2020. Training Generative Adversarial Networks with Limited Data. In Proc. NeurIPS."},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. NeurIPS.","author":"Karras Tero","year":"2021","unstructured":"Tero Karras, Miika Aittala, Samuli Laine, Erik H\"ark\u00f6nen, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2021. Alias-Free Generative Adversarial Networks. In Proc. NeurIPS."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01463"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01864"},{"volume-title":"International Conference on 3D Vision (3DV).","author":"Liao Tingting","key":"e_1_3_2_1_33_1","unstructured":"Tingting Liao, Hongwei Yi, Yuliang Xiu, Jiaxiang Tang, Yangyi Huang, Justus Thies, and Michael J. Black. 2024. TADA! Text to Animatable Digital Avatars. In International Conference on 3D Vision (3DV)."},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=0cpM2ApF9p6","author":"Liu Zhen","year":"2023","unstructured":"Zhen Liu, Yao Feng, Michael J. Black, Derek Nowrouzezahrai, Liam Paull, and Weiyang Liu. 2023. MeshDiffusion: Score-based Generative 3D Mesh Modeling. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=0cpM2ApF9p6"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459863"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_1_37_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_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"e_1_3_2_1_39_1","volume-title":"Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations. In European Conference on Computer Vision.","author":"Noguchi Atsuhiro","year":"2022","unstructured":"Atsuhiro Noguchi, Xiao Sun, Stephen Lin, and Tatsuya Harada. 2022. Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_40_1","first-page":"67021","article-title":"Autodecoding latent 3d diffusion models","volume":"36","author":"Ntavelis Evangelos","year":"2023","unstructured":"Evangelos Ntavelis, Aliaksandr Siarohin, Kyle Olszewski, Chaoyang Wang, Luc V Gool, and Sergey Tulyakov. 2023. Autodecoding latent 3d diffusion models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 67021--67047.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13503--13513","author":"Or-El Roy","year":"2022","unstructured":"Roy Or-El, Xuan Luo, Mengyi Shan, Eli Shechtman, Jeong Joon Park, and Ira Kemelmacher-Shlizerman. 2022. StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13503--13513."},{"volume-title":"Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR).","author":"Pavlakos Georgios","key":"e_1_3_2_1_42_1","unstructured":"Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, and Michael J. Black. 2019. Expressive Body Capture: 3D Hands, Face, and Body from a Single Image. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_43_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=FjNys5c7VyY","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=FjNys5c7VyY"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073239"},{"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 Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference, Munich, Germany, October 5--9, 2015, proceedings, part III 18. Springer, 234--241."},{"key":"e_1_3_2_1_47_1","volume-title":"Progressive Distillation for Fast Sampling of Diffusion Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TIdIXIpzhoI","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. https:\/\/openreview.net\/forum?id=TIdIXIpzhoI"},{"key":"e_1_3_2_1_48_1","volume-title":"SCULPT: Shape-conditioned unpaired learning of pose-dependent clothed and textured human meshes. arXiv preprint arXiv:2308.10638","author":"Sanyal Soubhik","year":"2023","unstructured":"Soubhik Sanyal, Partha Ghosh, Jinlong Yang, Michael J Black, Justus Thies, and Timo Bolkart. 2023. SCULPT: Shape-conditioned unpaired learning of pose-dependent clothed and textured human meshes. arXiv preprint arXiv:2308.10638 (2023)."},{"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. Advances in Neural Information Processing Systems, Vol. 33 (2020), 20154--20166.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","unstructured":"Tianchang Shen Jun Gao Kangxue Yin Ming-Yu Liu and Sanja Fidler. 2021. Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"e_1_3_2_1_52_1","volume-title":"3rd International Conference on Learning Representations (ICLR","author":"Simonyan K","year":"2015","unstructured":"K Simonyan and A Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations (ICLR 2015), 1--14."},{"key":"e_1_3_2_1_53_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PxTIG12RRHS","author":"Song Yang","year":"2021","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2021. Score-Based Generative Modeling through Stochastic Differential Equations. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PxTIG12RRHS"},{"key":"e_1_3_2_1_54_1","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang Tengfei","year":"2022","unstructured":"Tengfei Wang, Bo Zhang, Ting Zhang, Shuyang Gu, Jianmin Bao, Tadas Baltruaitis, Jingjing Shen, Dong Chen, Fang Wen, Qifeng Chen, and Baining Guo. 2022. RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022), 4563--4573."},{"key":"e_1_3_2_1_55_1","unstructured":"Zhengyi Wang Cheng Lu Yikai Wang Fan Bao Chongxuan Li Hang Su and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480545"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00852"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"e_1_3_2_1_59_1","volume-title":"LION: Latent Point Diffusion Models for 3D Shape Generation. In Advances in Neural Information Processing Systems (NeurIPS).","author":"Zeng Xiaohui","year":"2022","unstructured":"Xiaohui Zeng, Arash Vahdat, Francis Williams, Zan Gojcic, Or Litany, Sanja Fidler, and Karsten Kreis. 2022. LION: Latent Point Diffusion Models for 3D Shape Generation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","unstructured":"Jianfeng Zhang Zihang Jiang Dingdong Yang Hongyi Xu Yichun Shi Guoxian Song Zhongcong Xu Xinchao Wang and Jiashi Feng. 2022. AvatarGen: A 3D Generative Model for Animatable Human Avatars. In Arxiv.","DOI":"10.1007\/978-3-031-25066-8_39"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","unstructured":"Xuanmeng Zhang Jianfeng Zhang Chacko Rohan Hongyi Xu Guoxian Song Yi Yang and Jiashi Feng. 2023. GETAvatar: Generative Textured Meshes for Animatable Human Avatars. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00216"}],"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\/3664647.3681409","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:46Z","timestamp":1750294666000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681409"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":61,"alternative-id":["10.1145\/3664647.3681409","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681409","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"}}]}}