{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:33Z","timestamp":1776931173053,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":110,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763839","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":0,"title":["Single-Image 3D Human Reconstruction with 3D-Aware Diffusion Priors and Facial Enhancement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6503-8312","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9489-7385","authenticated-orcid":false,"given":"Bo-Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4736-8100","authenticated-orcid":false,"given":"Feng-Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0284-726X","authenticated-orcid":false,"given":"Hongbo","family":"Fu","sequence":"additional","affiliation":[{"name":"Division of Arts and Machine Creativity, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-5680","authenticated-orcid":false,"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1021-8148","authenticated-orcid":false,"given":"Lin","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00022"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00875"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00238"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02007"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383340"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00552"},{"key":"e_1_3_3_2_9_1","unstructured":"Yukang Cao Yan-Pei Cao Kai Han Ying Shan and Kwan-Yee\u00a0K Wong. 2024. DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models. Computer Vision and Pattern Recognition (CVPR) (2024)."},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00275"},{"key":"e_1_3_3_2_11_1","unstructured":"Zhe Cao Gines Hidalgo Martinez Tomas Simon Shih-En Wei and Yaser Sheikh. 2019. OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields. Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2019)."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_3_2_13_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Chang Di","year":"2023","unstructured":"Di Chang, Yichun Shi, Quankai Gao, Hongyi Xu, Jessica Fu, Guoxian Song, Qing Yan, Yizhe Zhu, Xiao Yang, and Mohammad Soleymani. 2023. Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00274"},{"key":"e_1_3_3_2_15_1","unstructured":"Hyung\u00a0Won Chung Noah Constant Xavier Garcia Adam Roberts Yi Tay Sharan Narang and Orhan Firat. 2023. Unimax: Fairer and more effective language sampling for large-scale multilingual pretraining. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.09151 (2023)."},{"key":"e_1_3_3_2_16_1","volume-title":"Computer Vision and Pattern Recognition (CVPR)","author":"Corona Enric","year":"2023","unstructured":"Enric Corona, Mihai Zanfir, Thiemo Alldieck, Eduard Gabriel\u00a0Bazavan, Andrei Zanfir, and Cristian Sminchisescu. 2023. Structured 3D Features for Reconstructing Relightable and Animatable Avatars. In Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Matt Deitke Ruoshi Liu Matthew Wallingford Huong Ngo Oscar Michel Aditya Kusupati Alan Fan Christian Laforte Vikram Voleti Samir\u00a0Yitzhak Gadre Eli VanderBilt Aniruddha Kembhavi Carl Vondrick Georgia Gkioxari Kiana Ehsani Ludwig Schmidt and Ali Farhadi. 2023a. Objaverse-XL: A Universe of 10M+ 3D Objects. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.05663 (2023).","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_3_2_20_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Lin Gao Jie Yang Bo-Tao Zhang Jia-Mu Sun Yu-Jie Yuan Hongbo Fu and Yu-Kun Lai. 2024. Real-time large-scale deformation of Gaussian Splatting. Transactions on Graphics (TOG) 43 6 (2024) 1\u201317.","DOI":"10.1145\/3687756"},{"key":"e_1_3_3_2_22_1","unstructured":"Xiangjun Gao Jiaolong Yang Jongyoo Kim Sida Peng Zicheng Liu and Xin Tong. 2022. Mps-nerf: Generalizable 3d human rendering from multiview images. Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2022)."},{"key":"e_1_3_3_2_23_1","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.00752 (2023)."},{"key":"e_1_3_3_2_24_1","unstructured":"Jianzhu Guo Dingyun Zhang Xiaoqiang Liu Zhizhou Zhong Yuan Zhang Pengfei Wan and Di Zhang. 2024b. 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_25_1","unstructured":"Minghao Guo Bohan Wang Kaiming He and Wojciech Matusik. 2024a. TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.20283 (2024)."},{"key":"e_1_3_3_2_26_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_27_1","unstructured":"Ruhs Henry. 2024. FaceFusion. https:\/\/github.com\/facefusion\/facefusion."},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00058"},{"key":"e_1_3_3_2_29_1","first-page":"8153","volume-title":"Computer Vision and Pattern Recognition (CVPR)","author":"Hu Li","year":"2024","unstructured":"Li Hu. 2024. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In Computer Vision and Pattern Recognition (CVPR). 8153\u20138163."},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00152"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01322"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"e_1_3_3_2_33_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_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"e_1_3_3_2_35_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. Transactions on Graphics (TOG) 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_36_1","unstructured":"Tobias Kirschstein Shenhan Qian Simon Giebenhain Tim Walter and Matthias Nie\u00dfner. 2023. NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.03027 (2023)."},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00234"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_19"},{"key":"e_1_3_3_2_40_1","unstructured":"Peng Li Yuan Liu Xiaoxiao Long Feihu Zhang Cheng Lin Mengfei Li Xingqun Qi Shanghang Zhang Wenhan Luo Ping Tan et\u00a0al. 2024a. Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention. Conference on Neural Information Processing Systems (NeurIPS) (2024)."},{"key":"e_1_3_3_2_41_1","unstructured":"Peng Li Wangguandong Zheng Yuan Liu Tao Yu Yangguang Li Xingqun Qi Mengfei Li Xiaowei Chi Siyu Xia Wei Xue et\u00a0al. 2024b. PSHuman: Photorealistic Single-view Human Reconstruction using Cross-Scale Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.10141 (2024)."},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_4"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"crossref","unstructured":"Tianye Li Timo Bolkart Michael\u00a0J Black Hao Li and Javier Romero. 2017. Learning a model of facial shape and expression from 4D scans. Transactions on Graphics (TOG) 36 6 (2017) 194\u20131.","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00054"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657501"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"crossref","unstructured":"Shiguang Liu and Jiaqi Hao. 2022. Generating talking face with controllable eye movements by disentangled blinking feature. Transactions on Visualization and Computer Graphics (TVCG) 29 12 (2022) 5050\u20135061.","DOI":"10.1109\/TVCG.2022.3199412"},{"key":"e_1_3_3_2_49_1","unstructured":"Xingchao Liu Chengyue Gong and Qiang Liu. 2022. Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.03003 (2022)."},{"key":"e_1_3_3_2_50_1","unstructured":"Yuan Liu Cheng Lin Zijiao Zeng Xiaoxiao Long Lingjie Liu Taku Komura and Wenping Wang. 2023a. SyncDreamer: Generating multiview-consistent images from a single-view image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.03453 (2023)."},{"key":"e_1_3_3_2_51_1","unstructured":"Zhibin Liu Haoye Dong Aviral Chharia and Hefeng Wu. 2024. Human-vdm: Learning single-image 3d human gaussian splatting from video diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.02851 (2024)."},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"crossref","unstructured":"Matthew Loper Naureen Mahmood Javier Romero Gerard Pons-Moll and Michael\u00a0J. Black. 2015. SMPL: A Skinned Multi-Person Linear Model. Transactions on Graphics (TOG) (2015).","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_3_2_54_1","unstructured":"Yifang Men Yuan Yao Miaomiao Cui and Liefeng Bo. 2024. Mimo: Controllable character video synthesis with spatial decomposed modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.16160 (2024)."},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00571"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"crossref","unstructured":"Werner Palfinger. 2022. Continuous remeshing for inverse rendering. Computer Animation and Virtual Worlds 33 5 (2022) e2101.","DOI":"10.1002\/cav.2101"},{"key":"e_1_3_3_2_58_1","unstructured":"Panwang Pan Zhuo Su Chenguo Lin Zhen Fan Yongjie Zhang Zeming Li Tingting Shen Yadong Mu and Yebin Liu. 2024. HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors. Conference on Neural Information Processing Systems (NeurIPS) (2024)."},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"crossref","unstructured":"Sida Peng Chen Geng Yuanqing Zhang Yinghao Xu Qianqian Wang Qing Shuai Xiaowei Zhou and Hujun Bao. 2023. Implicit Neural Representations with Structured Latent Codes for Human Body Modeling. Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2023).","DOI":"10.1109\/TPAMI.2023.3245815"},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"e_1_3_3_2_63_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T Barron and Ben Mildenhall. 2022. DreamFusion: Text-to-3D using 2D diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14988 (2022)."},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"crossref","unstructured":"Shenhan Qian Tobias Kirschstein Liam Schoneveld Davide Davoli Simon Giebenhain and Matthias Nie\u00dfner. 2023. GaussianAvatars: Photorealistic head avatars with rigged 3D Gaussians. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.02069 (2023).","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"e_1_3_3_2_65_1","unstructured":"Lingteng Qiu Xiaodong Gu Peihao Li Qi Zuo Weichao Shen Junfei Zhang Kejie Qiu Weihao Yuan Guanying Chen Zilong Dong et\u00a0al. 2025. LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.10625 (2025)."},{"key":"e_1_3_3_2_66_1","unstructured":"Linzi Qu Jiaxiang Shang Miu-Ling Lam and Hongbo Fu. 2025. Controllable Human Video Generation from Sparse Sketches. IEEE Transactions on Visualization and Computer Graphics (2025)."},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"e_1_3_3_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"e_1_3_3_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00291"},{"key":"e_1_3_3_2_71_1","unstructured":"Ruizhi Shao Youxin Pang Zerong Zheng Jingxiang Sun and Yebin Liu. 2024a. Human4DiT: Free-view Human Video Generation with 4D Diffusion Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.17405 (2024)."},{"key":"e_1_3_3_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"e_1_3_3_2_73_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. Conference on Neural Information Processing Systems (NeurIPS) 34 (2021) 6087\u20136101."},{"key":"e_1_3_3_2_74_1","unstructured":"Yichun Shi Peng Wang Jianglong Ye Long Mai Kejie Li and Xiao Yang. 2024. MVDream: Multi-view Diffusion for 3D Generation. International Conference on Learning Representations (ICLR) (2024)."},{"key":"e_1_3_3_2_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00543"},{"key":"e_1_3_3_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01289"},{"key":"e_1_3_3_2_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00650"},{"key":"e_1_3_3_2_78_1","doi-asserted-by":"crossref","unstructured":"Shitao Tang Jiacheng Chen Dilin Wang Chengzhou Tang Fuyang Zhang Yuchen Fan Vikas Chandra Yasutaka Furukawa and Rakesh Ranjan. 2024. MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.12712 (2024).","DOI":"10.1007\/978-3-031-72640-8_10"},{"key":"e_1_3_3_2_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_3_3_2_80_1","unstructured":"Shuyuan Tu Zhen Xing Xintong Han Zhi-Qi Cheng Qi Dai Chong Luo and Zuxuan Wu. 2024. StableAnimator: High-Quality Identity-Preserving Human Image Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.17697 (2024)."},{"key":"e_1_3_3_2_81_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"e_1_3_3_2_82_1","unstructured":"Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang Jianyuan Zeng et\u00a0al. 2025a. Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20314 (2025)."},{"key":"e_1_3_3_2_83_1","unstructured":"Qilin Wang Zhengkai Jiang Chengming Xu Jiangning Zhang Yabiao Wang Xinyi Zhang Yun Cao Weijian Cao Chengjie Wang and Yanwei Fu. 2024a. VividPose: Advancing Stable Video Diffusion for Realistic Human Image Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.18156 (2024)."},{"key":"e_1_3_3_2_84_1","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 e-prints (2023) arXiv\u20132307."},{"key":"e_1_3_3_2_85_1","unstructured":"Xiang Wang Shiwei Zhang Changxin Gao Jiayu Wang Xiaoqiang Zhou Yingya Zhang Luxin Yan and Nong Sang. 2024b. UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.01188 (2024)."},{"key":"e_1_3_3_2_86_1","unstructured":"Xiang Wang Shiwei Zhang Longxiang Tang Yingya Zhang Changxin Gao Yuehuan Wang and Nong Sang. 2025b. UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.11289 (2025)."},{"key":"e_1_3_3_2_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00628"},{"key":"e_1_3_3_2_88_1","doi-asserted-by":"crossref","unstructured":"Zhou Wang Alan\u00a0C Bovik Hamid\u00a0R Sheikh and Eero\u00a0P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. Transactions on Image Processing (TIP) 13 4 (2004) 600\u2013612.","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_2_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"e_1_3_3_2_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00175"},{"key":"e_1_3_3_2_91_1","unstructured":"Pingyu Wu Kai Zhu Yu Liu Liming Zhao Wei Zhai Yang Cao and Zheng-Jun Zha. 2024. Improved Video VAE for Latent Video Diffusion Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.06449 (2024)."},{"key":"e_1_3_3_2_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"e_1_3_3_2_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"e_1_3_3_2_94_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_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"e_1_3_3_2_96_1","unstructured":"Yuxuan Xue Xianghui Xie Riccardo Marin and Gerard Pons-Moll. 2024. Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.08475 (2024)."},{"key":"e_1_3_3_2_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681634"},{"key":"e_1_3_3_2_98_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"e_1_3_3_2_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591555"},{"key":"e_1_3_3_2_100_1","doi-asserted-by":"crossref","unstructured":"Huichao Zhang Bowen Chen Hao Yang Liao Qu Xu Wang Li Chen Chao Long Feida Zhu Kang Du and Min Zheng. 2023. AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose. Conference on Artificial Intelligence (AAAI) (2023).","DOI":"10.1609\/aaai.v38i7.28540"},{"key":"e_1_3_3_2_101_1","doi-asserted-by":"crossref","unstructured":"Longwen Zhang Ziyu Wang Qixuan Zhang Qiwei Qiu Anqi Pang Haoran Jiang Wei Yang Lan Xu and Jingyi Yu. 2024b. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets. Transactions on Graphics (TOG) 43 4 (2024) 1\u201320.","DOI":"10.1145\/3658146"},{"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","unstructured":"Yuang Zhang Jiaxi Gu Li-Wen Wang Han Wang Junqi Cheng Yuefeng Zhu and Fangyuan Zou. 2024a. Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.19680 (2024)."},{"key":"e_1_3_3_2_104_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00948"},{"key":"e_1_3_3_2_105_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01318"},{"key":"e_1_3_3_2_106_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"e_1_3_3_2_107_1","unstructured":"Shangchen Zhou Kelvin Chan Chongyi Li and Chen\u00a0Change Loy. 2022. Towards robust blind face restoration with codebook lookup transformer. Conference on Neural Information Processing Systems (NeurIPS) 35 (2022) 30599\u201330611."},{"key":"e_1_3_3_2_108_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00462"},{"key":"e_1_3_3_2_109_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"e_1_3_3_2_110_1","doi-asserted-by":"crossref","unstructured":"Yiyu Zhuang Jiaxi Lv Hao Wen Qing Shuai Ailing Zeng Hao Zhu Shifeng Chen Yujiu Yang Xun Cao and Wei Liu. 2024. IDOL: Instant Photorealistic 3D Human Creation from a Single Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.14963 (2024).","DOI":"10.1109\/CVPR52734.2025.02450"},{"key":"e_1_3_3_2_111_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00444"}],"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\/3757377.3763839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:24:06Z","timestamp":1765250646000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763839"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":110,"alternative-id":["10.1145\/3757377.3763839","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763839","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"}}]}}