{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T11:42:06Z","timestamp":1783597326825,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":88,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T00:00:00Z","timestamp":1702166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,10]]},"DOI":"10.1145\/3610548.3618153","type":"proceedings-article","created":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T12:28:40Z","timestamp":1702297720000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["Single-Image 3D Human Digitization with Shape-guided Diffusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5359-0118","authenticated-orcid":false,"given":"Badour","family":"Albahar","sequence":"first","affiliation":[{"name":"Kuwait University, Kuwait"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2053-3472","authenticated-orcid":false,"given":"Shunsuke","family":"Saito","sequence":"additional","affiliation":[{"name":"Meta, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0714-1669","authenticated-orcid":false,"given":"Hung-Yu","family":"Tseng","sequence":"additional","affiliation":[{"name":"Meta, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6541-8825","authenticated-orcid":false,"given":"Changil","family":"Kim","sequence":"additional","affiliation":[{"name":"Meta, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6628-8084","authenticated-orcid":false,"given":"Johannes","family":"Kopf","sequence":"additional","affiliation":[{"name":"Meta, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0536-3658","authenticated-orcid":false,"given":"Jia-Bin","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Maryland, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,12,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Kfir Aberman Mingyi Shi Jing Liao Dani Lischinski Baoquan Chen and Daniel Cohen-Or. 2019. Deep video-based performance cloning. In Computer Graphics Forum Vol.\u00a038. 219\u2013233.","DOI":"10.1111\/cgf.13632"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Badour AlBahar and Jia-Bin Huang. 2019. Guided image-to-image translation with bi-directional feature transformation. In ICCV.","DOI":"10.1109\/ICCV.2019.00911"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480559"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Thiemo Alldieck Marcus Magnor Bharat\u00a0Lal Bhatnagar Christian Theobalt and Gerard Pons-Moll. 2019a. Learning to reconstruct people in clothing from a single RGB camera. In CVPR.","DOI":"10.1109\/CVPR.2019.00127"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Thiemo Alldieck Gerard Pons-Moll Christian Theobalt and Marcus Magnor. 2019b. Tex2shape: Detailed full human body geometry from a single image. In ICCV.","DOI":"10.1109\/ICCV.2019.00238"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Thiemo Alldieck Mihai Zanfir and Cristian Sminchisescu. 2022a. Photorealistic monocular 3d reconstruction of humans wearing clothing. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Thiemo Alldieck Mihai Zanfir and Cristian Sminchisescu. 2022b. Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459850"},{"key":"e_1_3_2_1_9_1","unstructured":"Alexander\u00a0W. Bergman Petr Kellnhofer Wang Yifan Eric\u00a0R. Chan David\u00a0B. Lindell and Gordon Wetzstein. 2022. Generative Neural Articulated Radiance Fields. In NeurIPS."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Bharat\u00a0Lal Bhatnagar Garvita Tiwari Christian Theobalt and Gerard Pons-Moll. 2019. Multi-garment net: Learning to dress 3d people from images. In ICCV.","DOI":"10.1109\/ICCV.2019.00552"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383309"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Caroline Chan Shiry Ginosar Tinghui Zhou and Alexei\u00a0A Efros. 2019. Everybody dance now. In ICCV.","DOI":"10.1109\/ICCV.2019.00603"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Eric\u00a0R Chan Connor\u00a0Z Lin Matthew\u00a0A Chan Koki Nagano Boxiao Pan Shalini De\u00a0Mello Orazio Gallo Leonidas\u00a0J Guibas Jonathan Tremblay Sameh Khamis 2022. Efficient geometry-aware 3D generative adversarial networks. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Eric\u00a0R Chan Marco Monteiro Petr Kellnhofer Jiajun Wu and Gordon Wetzstein. 2021. pi-gan: Periodic implicit generative adversarial networks for 3d-aware image synthesis. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Rui Chen Yongwei Chen Ningxin Jiao and Kui Jia. 2023. Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation. In ICCV.","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_2_1_16_1","volume-title":"MonoNHR: Monocular Neural Human Renderer. International Conference on 3D Vision.","author":"Choi Hongsuk","year":"2022","unstructured":"Hongsuk Choi, Gyeongsik Moon, Matthieu Armando, Vincent Leroy, Kyoung\u00a0Mu Lee, and Gregory Rogez. 2022. MonoNHR: Monocular Neural Human Renderer. International Conference on 3D Vision."},{"key":"e_1_3_2_1_17_1","volume-title":"Smplicit: Topology-aware generative model for clothed people. In CVPR.","author":"Corona Enric","year":"2021","unstructured":"Enric Corona, Albert Pumarola, Guillem Alenya, Gerard Pons-Moll, and Francesc Moreno-Noguer. 2021. Smplicit: Topology-aware generative model for clothed people. In CVPR."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","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 CVPR.","DOI":"10.1109\/CVPR52729.2023.01626"},{"key":"e_1_3_2_1_19_1","volume-title":"Stylegan-human: A data-centric odyssey of human generation. In ECCV.","author":"Fu Jianglin","year":"2022","unstructured":"Jianglin Fu, Shikai Li, Yuming Jiang, Kwan-Yee Lin, Chen Qian, Chen\u00a0Change Loy, Wayne Wu, and Ziwei Liu. 2022. Stylegan-human: A data-centric odyssey of human generation. In ECCV."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Valentin Gabeur Jean-S\u00e9bastien Franco Xavier Martin Cordelia Schmid and Gregory Rogez. 2019. Moulding humans: Non-parametric 3d human shape estimation from single images. In ICCV.","DOI":"10.1109\/ICCV.2019.00232"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik Amit\u00a0H. Bermano Gal Chechik and Daniel Cohen-Or. 2022. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. (2022). https:\/\/doi.org\/10.48550\/ARXIV.2208.01618","DOI":"10.48550\/ARXIV.2208.01618"},{"key":"e_1_3_2_1_22_1","volume-title":"MPS-NeRF: Generalizable 3D Human Rendering From Multiview Images","author":"Gao Xiangjun","year":"2022","unstructured":"Xiangjun Gao, Jiaolong Yang, Jongyoo Kim, Sida Peng, Zicheng Liu, and Xin Tong. 2022. MPS-NeRF: Generalizable 3D Human Rendering From Multiview Images. IEEE TPAMI (2022), 1\u201312."},{"key":"e_1_3_2_1_23_1","volume-title":"Densepose: Dense human pose estimation in the wild. In CVPR.","author":"G\u00fcler R\u0131za\u00a0Alp","year":"2018","unstructured":"R\u0131za\u00a0Alp G\u00fcler, Natalia Neverova, and Iasonas Kokkinos. 2018. Densepose: Dense human pose estimation in the wild. In CVPR."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01086"},{"key":"e_1_3_2_1_25_1","unstructured":"Fangzhou Hong Zhaoxi Chen Yushi Lan Liang Pan and Ziwei Liu. 2023. EVA3D: Compositional 3D Human Generation from 2D Image Collections. In ICLR."},{"key":"e_1_3_2_1_26_1","volume-title":"SHERF: Generalizable Human NeRF from a Single Image. In ICCV.","author":"Hu Shoukang","year":"2023","unstructured":"Shoukang Hu, Fangzhou Hong, Liang Pan, Haiyi Mei, Lei Yang, and Ziwei Liu. 2023. SHERF: Generalizable Human NeRF from a Single Image. In ICCV."},{"key":"e_1_3_2_1_27_1","volume-title":"One-shot Implicit Animatable Avatars with Model-based Priors. arXiv preprint arXiv:2212.02469","author":"Huang Yangyi","year":"2022","unstructured":"Yangyi Huang, Hongwei Yi, Weiyang Liu, Haofan Wang, Boxi Wu, Wenxiao Wang, Binbin Lin, Debing Zhang, and Deng Cai. 2022. One-shot Implicit Animatable Avatars with Model-based Priors. arXiv preprint arXiv:2212.02469 (2022)."},{"key":"e_1_3_2_1_28_1","volume-title":"Arch: Animatable reconstruction of clothed humans. In CVPR.","author":"Huang Zeng","year":"2020","unstructured":"Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, and Tony Tung. 2020. Arch: Animatable reconstruction of clothed humans. In CVPR."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Angjoo Kanazawa Michael\u00a0J Black David\u00a0W Jacobs and Jitendra Malik. 2018. End-to-end recovery of human shape and pose. In CVPR.","DOI":"10.1109\/CVPR.2018.00744"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Samuli Laine and Timo Aila. 2019. A style-based generator architecture for generative adversarial networks. In CVPR.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Samuli Laine Miika Aittala Janne Hellsten Jaakko Lehtinen and Timo Aila. 2020. Analyzing and improving the image quality of stylegan. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Nikos Kolotouros Georgios Pavlakos Michael\u00a0J Black and Kostas Daniilidis. 2019. Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In ICCV.","DOI":"10.1109\/ICCV.2019.00234"},{"key":"e_1_3_2_1_33_1","volume-title":"Neural human performer: Learning generalizable radiance fields for human performance rendering. Advances in Neural Information Processing Systems 34","author":"Kwon Youngjoong","year":"2021","unstructured":"Youngjoong Kwon, Dahun Kim, Duygu Ceylan, and Henry Fuchs. 2021. Neural human performer: Learning generalizable radiance fields for human performance rendering. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Christoph Lassner Javier Romero Martin Kiefel Federica Bogo Michael\u00a0J Black and Peter\u00a0V Gehler. 2017. Unite the people: Closing the loop between 3d and 2d human representations. In CVPR.","DOI":"10.1109\/CVPR.2017.500"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459884"},{"key":"e_1_3_2_1_36_1","unstructured":"Chen-Hsuan Lin Jun Gao Luming Tang Towaki Takikawa Xiaohui Zeng Xun Huang Karsten Kreis Sanja Fidler Ming-Yu Liu and Tsung-Yi Lin. 2023. Magic3D: High-Resolution Text-to-3D Content Creation. In CVPR."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480528"},{"key":"e_1_3_2_1_38_1","volume-title":"Liquid warping GAN with attention: A unified framework for human image synthesis","author":"Liu Wen","year":"2021","unstructured":"Wen Liu, Zhixin Piao, Zhi Tu, Wenhan Luo, Lin Ma, and Shenghua Gao. 2021b. Liquid warping GAN with attention: A unified framework for human image synthesis. IEEE TPAMI (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Ziwei Liu Ping Luo Shi Qiu Xiaogang Wang and Xiaoou Tang. 2016. DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations. In CVPR.","DOI":"10.1109\/CVPR.2016.124"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_1_41_1","first-page":"163","article-title":"Marching cubes: A high resolution 3D surface construction algorithm","volume":"21","author":"Lorensen E","year":"1987","unstructured":"William\u00a0E Lorensen and Harvey\u00a0E Cline. 1987. Marching cubes: A high resolution 3D surface construction algorithm. ACM TOG 21, 4 (1987), 163\u2013169.","journal-title":"ACM TOG"},{"key":"e_1_3_2_1_42_1","unstructured":"Liqian Ma Xu Jia Qianru Sun Bernt Schiele Tinne Tuytelaars and Luc Van\u00a0Gool. 2017. Pose guided person image generation. In NeurIPS."},{"key":"e_1_3_2_1_43_1","unstructured":"Liqian Ma Qianru Sun Stamatios Georgoulis Luc Van\u00a0Gool Bernt Schiele and Mario Fritz. 2018. Disentangled person image generation. In CVPR."},{"key":"e_1_3_2_1_44_1","unstructured":"Yifang Men Yiming Mao Yuning Jiang Wei-Ying Ma and Zhouhui Lian. 2020. Controllable person image synthesis with attribute-decomposed gan. In CVPR."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Gal Metzer Elad Richardson Or Patashnik Raja Giryes and Daniel Cohen-Or. 2023. Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Marko Mihajlovic Aayush Bansal Michael Zollhoefer Siyu Tang and Shunsuke Saito. 2022. KeypointNeRF: Generalizing image-based volumetric avatars using relative spatial encoding of keypoints. In ECCV.","DOI":"10.1007\/978-3-031-19784-0_11"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P. Srinivasan Matthew Tancik Jonathan\u00a0T. 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_48_1","volume-title":"Siclope: Silhouette-based clothed people. In CVPR.","author":"Natsume Ryota","year":"2019","unstructured":"Ryota Natsume, Shunsuke Saito, Zeng Huang, Weikai Chen, Chongyang Ma, Hao Li, and Shigeo Morishima. 2019. Siclope: Silhouette-based clothed people. In CVPR."},{"key":"e_1_3_2_1_49_1","volume-title":"Giraffe: Representing scenes as compositional generative neural feature fields. In CVPR.","author":"Niemeyer Michael","year":"2021","unstructured":"Michael Niemeyer and Andreas Geiger. 2021. Giraffe: Representing scenes as compositional generative neural feature fields. In CVPR."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Michael Oechsle Lars Mescheder Michael Niemeyer Thilo Strauss and Andreas Geiger. 2019. Texture fields: Learning texture representations in function space. In ICCV.","DOI":"10.1109\/ICCV.2019.00463"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Gaurav Parmar Richard Zhang and Jun-Yan Zhu. 2022. On Aliased Resizing and Surprising Subtleties in GAN Evaluation. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Georgios Pavlakos Luyang Zhu Xiaowei Zhou and Kostas Daniilidis. 2018. Learning to estimate 3D human pose and shape from a single color image. In CVPR.","DOI":"10.1109\/CVPR.2018.00055"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Sida Peng Junting Dong Qianqian Wang Shangzhan Zhang Qing Shuai Xiaowei Zhou and Hujun Bao. 2021a. Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"e_1_3_2_1_54_1","volume-title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans. In CVPR.","author":"Peng Sida","year":"2021","unstructured":"Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, and Xiaowei Zhou. 2021b. Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans. In CVPR."},{"key":"e_1_3_2_1_55_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T. Barron and Ben Mildenhall. 2022. DreamFusion: Text-to-3D using 2D Diffusion. In ICLR."},{"key":"e_1_3_2_1_56_1","volume-title":"Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors. arXiv preprint arXiv:2306.17843","author":"Qian Guocheng","year":"2023","unstructured":"Guocheng Qian, Jinjie Mai, Abdullah Hamdi, Jian Ren, Aliaksandr Siarohin, Bing Li, Hsin-Ying Lee, Ivan Skorokhodov, Peter Wonka, Sergey Tulyakov, and Bernard Ghanem. 2023. Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors. arXiv preprint arXiv:2306.17843 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","unstructured":"Yurui Ren Xiaoming Yu Junming Chen Thomas\u00a0H Li and Ge Li. 2020. Deep image spatial transformation for person image generation. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"e_1_3_2_1_58_1","volume-title":"TEXTure: Text-Guided Texturing of 3D Shapes. ACM TOG","author":"Richardson Elad","year":"2023","unstructured":"Elad Richardson, Gal Metzer, Yuval Alaluf, Raja Giryes, and Daniel Cohen-Or. 2023. TEXTure: Text-Guided Texturing of 3D Shapes. ACM TOG (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Moab\u00a0Arar.","author":"Yuval Atzmon","year":"2023","unstructured":"Yuval Atzmon Amit H. Bermano Gal Chechik Daniel Cohen-Or Rinon\u00a0Gal, Moab\u00a0Arar. 2023. Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models. (2023). https:\/\/arxiv.org\/abs\/2302.12228"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","unstructured":"Xuejian Rong Jia-Bin Huang Ayush Saraf Changil Kim and Johannes Kopf. 2022. Boosting View Synthesis with Residual Transfer. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01914"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Nataniel Ruiz Yuanzhen Li Varun Jampani Yael Pritch Michael Rubinstein and Kfir Aberman. 2022. DreamBooth: Fine Tuning Text-to-image Diffusion Models for Subject-Driven Generation. (2022).","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"crossref","unstructured":"Shunsuke Saito Zeng Huang Ryota Natsume Shigeo Morishima Angjoo Kanazawa and Hao Li. 2019. PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization. In ICCV.","DOI":"10.1109\/ICCV.2019.00239"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Shunsuke Saito Tomas Simon Jason Saragih and Hanbyul Joo. 2020. PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"crossref","unstructured":"Shunsuke Saito Jinlong Yang Qianli Ma and Michael\u00a0J Black. 2021. SCANimate: Weakly supervised learning of skinned clothed avatar networks. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00291"},{"key":"e_1_3_2_1_67_1","volume-title":"Style and Pose Control for Image Synthesis of Humans from a Single Monocular View. arXiv preprint arXiv:2102.11263","author":"Sarkar Kripasindhu","year":"2021","unstructured":"Kripasindhu Sarkar, Vladislav Golyanik, Lingjie Liu, and Christian Theobalt. 2021. Style and Pose Control for Image Synthesis of Humans from a Single Monocular View. arXiv preprint arXiv:2102.11263 (2021)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Aliaksandr Siarohin Enver Sangineto St\u00e9phane Lathuiliere and Nicu Sebe. 2018. Deformable gans for pose-based human image generation. In CVPR.","DOI":"10.1109\/CVPR.2018.00359"},{"key":"e_1_3_2_1_69_1","volume-title":"Facsimile: Fast and accurate scans from an image in less than a second. In ICCV.","author":"Smith David","year":"2019","unstructured":"David Smith, Matthew Loper, Xiaochen Hu, Paris Mavroidis, and Javier Romero. 2019. Facsimile: Fast and accurate scans from an image in less than a second. In ICCV."},{"key":"e_1_3_2_1_70_1","volume-title":"Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior. arXiv preprint arXiv:2303.14184","author":"Tang Junshu","year":"2023","unstructured":"Junshu Tang, Tengfei Wang, Bo Zhang, Ting Zhang, Ran Yi, Lizhuang Ma, and Dong Chen. 2023. Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior. arXiv preprint arXiv:2303.14184 (2023)."},{"key":"e_1_3_2_1_71_1","volume-title":"Bodynet: Volumetric inference of 3d human body shapes. In ECCV.","author":"Varol Gul","year":"2018","unstructured":"Gul Varol, Duygu Ceylan, Bryan Russell, Jimei Yang, Ersin Yumer, Ivan Laptev, and Cordelia Schmid. 2018. Bodynet: Volumetric inference of 3d human body shapes. In ECCV."},{"key":"e_1_3_2_1_72_1","volume-title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation. arXiv preprint arXiv:2212.00774","author":"Wang Haochen","year":"2022","unstructured":"Haochen Wang, Xiaodan Du, Jiahao Li, Raymond\u00a0A. Yeh, and Greg Shakhnarovich. 2022. Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation. arXiv preprint arXiv:2212.00774 (2022)."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"crossref","unstructured":"Lizhen Wang Xiaochen Zhao Tao Yu Songtao Wang and Yebin Liu. 2020. NormalGAN: Learning Detailed 3D Human from a Single RGB-D Image. In ECCV.","DOI":"10.1007\/978-3-030-58565-5_26"},{"key":"e_1_3_2_1_74_1","volume-title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. arXiv preprint arXiv:2305.16213","author":"Wang Zhengyi","year":"2023","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. arXiv preprint arXiv:2305.16213 (2023)."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"crossref","unstructured":"Chung-Yi Weng Brian Curless Pratul\u00a0P. Srinivasan Jonathan\u00a0T. Barron and Ira Kemelmacher-Shlizerman. 2022. HumanNeRF: Free-Viewpoint Rendering of Moving People From Monocular Video. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"e_1_3_2_1_76_1","volume-title":"3D-aware Image Generation using 2D Diffusion Models. arXiv preprint arXiv:2303.17905","author":"Xiang Jianfeng","year":"2023","unstructured":"Jianfeng Xiang, Jiaolong Yang, Binbin Huang, and Xin Tong. 2023. 3D-aware Image Generation using 2D Diffusion Models. arXiv preprint arXiv:2303.17905 (2023)."},{"key":"e_1_3_2_1_77_1","volume-title":"Computer Graphics Forum, Vol.\u00a041","author":"Xie Yiheng","unstructured":"Yiheng Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari, James Tompkin, Vincent Sitzmann, and Srinath Sridhar. 2022. Neural fields in visual computing and beyond. In Computer Graphics Forum, Vol.\u00a041. Wiley Online Library, 641\u2013676."},{"key":"e_1_3_2_1_78_1","volume-title":"ECON: Explicit Clothed humans Optimized via Normal integration. In CVPR.","author":"Xiu Yuliang","year":"2023","unstructured":"Yuliang Xiu, Jinlong Yang, Xu Cao, Dimitrios Tzionas, and Michael\u00a0J. Black. 2023. ECON: Explicit Clothed humans Optimized via Normal integration. In CVPR."},{"key":"e_1_3_2_1_79_1","volume-title":"ICON: Implicit Clothed humans Obtained from Normals. In CVPR.","author":"Xiu Yuliang","year":"2022","unstructured":"Yuliang Xiu, Jinlong Yang, Dimitrios Tzionas, and Michael\u00a0J. Black. 2022. ICON: Implicit Clothed humans Obtained from Normals. In CVPR."},{"key":"e_1_3_2_1_80_1","unstructured":"Dejia Xu Yifan Jiang Peihao Wang Zhiwen Fan Yi Wang and Zhangyang Wang. 2022. NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360\u00b0 Views. arXiv preprint arXiv:2211.16431."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"crossref","unstructured":"Jae\u00a0Shin Yoon Lingjie Liu Vladislav Golyanik Kripasindhu Sarkar Hyun\u00a0Soo Park and Christian Theobalt. 2021. Pose-Guided Human Animation from a Single Image in the Wild. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01479"},{"key":"e_1_3_2_1_82_1","unstructured":"Jonathan Young. 2021. xatlas: Mesh parameterization \/ UV unwrapping library. https:\/\/github.com\/jpcy\/xatlas."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"crossref","unstructured":"Tao Yu Zerong Zheng Kaiwen Guo Pengpeng Liu Qionghai Dai and Yebin Liu. 2021. Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"e_1_3_2_1_84_1","volume-title":"AvatarGen: A 3D Generative Model for Animatable Human Avatars. Arxiv","author":"Zhang Jianfeng","year":"2022","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. Arxiv (2022)."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. arxiv:2302.05543\u00a0[cs.CV]","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei\u00a0A Efros Eli Shechtman and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In CVPR.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_87_1","volume-title":"PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction","author":"Zheng Zerong","year":"2021","unstructured":"Zerong Zheng, Tao Yu, Yebin Liu, and Qionghai Dai. 2021. PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction. IEEE TPAMI (2021)."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"crossref","unstructured":"Zhen Zhu Tengteng Huang Baoguang Shi Miao Yu Bofei Wang and Xiang Bai. 2019. Progressive Pose Attention Transfer for Person Image Generation. In CVPR.","DOI":"10.1109\/CVPR.2019.00245"}],"event":{"name":"SA '23: SIGGRAPH Asia 2023","location":"Sydney NSW Australia","acronym":"SA '23","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2023 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610548.3618153","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610548.3618153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:33:51Z","timestamp":1755768831000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610548.3618153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,10]]},"references-count":88,"alternative-id":["10.1145\/3610548.3618153","10.1145\/3610548"],"URL":"https:\/\/doi.org\/10.1145\/3610548.3618153","relation":{},"subject":[],"published":{"date-parts":[[2023,12,10]]},"assertion":[{"value":"2023-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}