{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:41:25Z","timestamp":1755823285685,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"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":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612058","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"8626-8634","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["AniPixel: Towards Animatable Pixel-Aligned Human Avatar"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3221-8149","authenticated-orcid":false,"given":"Jinlong","family":"Fan","sequence":"first","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-7661","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2990-505X","authenticated-orcid":false,"given":"Zhi","family":"Hou","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Thiemo Alldieck Mihai Zanfir and Cristian Sminchisescu. 2022. Photorealistic Monocular 3D Reconstruction of HumansWearing Clothing. In CVPR. 1506--1515.","key":"e_1_3_2_1_1_1","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"e_1_3_2_1_2_1","volume-title":"Mvsnerf: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo. In ICCV. 14124--14133.","author":"Chen Anpei","year":"2021","unstructured":"Anpei Chen, Zexiang Xu, Fuqiang Zhao, Xiaoshuai Zhang, Fanbo Xiang, Jingyi Yu, and Hao Su. 2021. Mvsnerf: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo. In ICCV. 14124--14133."},{"key":"e_1_3_2_1_3_1","volume-title":"Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis. arXiv preprint arXiv:2204.11798","author":"Cheng Wei","year":"2022","unstructured":"Wei Cheng, Su Xu, Jingtan Piao, Chen Qian, Wayne Wu, Kwan-Yee Lin, and Hongsheng Li. 2022. Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis. arXiv preprint arXiv:2204.11798 (2022). arXiv:2204.11798"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1145\/2766945"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1145\/2897824.2925969"},{"key":"e_1_3_2_1_6_1","volume-title":"MPS-NeRF: Generalizable 3D Human Rendering From Multiview Images. TPAMI PP (Sept","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. TPAMI PP (Sept. 2022)."},{"key":"e_1_3_2_1_7_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, and Jason Dourgarian. 2019. The Relightables: Volumetric Performance Capture of Humans with Realistic Relighting. ACM Transactions on Graphics (ToG) 38, 6 (2019), 1--19.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"e_1_3_2_1_8_1","volume-title":"ARCH: Animation-ready Clothed Human Reconstruction Revisited. In ICCV. 11046--11056.","author":"He Tong","year":"2021","unstructured":"Tong He, Yuanlu Xu, Shunsuke Saito, Stefano Soatto, and Tony Tung. 2021. ARCH: Animation-ready Clothed Human Reconstruction Revisited. In ICCV. 11046--11056."},{"key":"e_1_3_2_1_9_1","volume-title":"Arch: Animatable Reconstruction of Clothed Humans. In CVPR. 3093--3102.","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. 3093--3102."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1109\/TPAMI.2013.248"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1145\/964965.808594"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1145\/1230100.1230107"},{"key":"e_1_3_2_1_13_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR (Poster)."},{"key":"e_1_3_2_1_14_1","volume-title":"Advances in Neural Information Processing Systems","volume":"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. In Advances in Neural Information Processing Systems, Vol. 34. Curran Associates, Inc., 24741--24752."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1145\/344779.344862"},{"unstructured":"Zhengqi Li Simon Niklaus Noah Snavely and Oliver Wang. 2021. Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes. In CVPR. 6498--6508.","key":"e_1_3_2_1_16_1"},{"key":"e_1_3_2_1_17_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) 40, 6 (2021), 1--16.","journal-title":"ACM Transactions on Graphics (TOG)"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1145\/3306346.3323020"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1145\/2816795.2818013"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1109\/2945.468400"},{"key":"e_1_3_2_1_21_1","volume-title":"Occupancy Networks: Learning 3d Reconstruction in Function Space. In CVPR. 4460--4470.","author":"Mescheder Lars","year":"2019","unstructured":"Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, and Andreas Geiger. 2019. Occupancy Networks: Learning 3d Reconstruction in Function Space. In CVPR. 4460--4470."},{"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.","key":"e_1_3_2_1_22_1","DOI":"10.1007\/978-3-031-19784-0_11"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1145\/3503250"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1145\/3528223.3530127"},{"doi-asserted-by":"crossref","unstructured":"Atsuhiro Noguchi Xiao Sun Stephen Lin and Tatsuya Harada. 2021. Neural Articulated Radiance Field. In ICCV. 5762--5772.","key":"e_1_3_2_1_25_1","DOI":"10.1109\/ICCV48922.2021.00571"},{"key":"e_1_3_2_1_26_1","volume-title":"Deepsdf: Learning Continuous Signed Distance Functions for Shape Representation. In CVPR. 165--174.","author":"Park Jeong Joon","year":"2019","unstructured":"Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. 2019. Deepsdf: Learning Continuous Signed Distance Functions for Shape Representation. In CVPR. 165--174."},{"key":"e_1_3_2_1_27_1","volume-title":"Nerfies: Deformable Neural Radiance Fields. In ICCV. 5865--5874.","author":"Park Keunhong","year":"2021","unstructured":"Keunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz, Dan B. Goldman, Steven M. Seitz, and Ricardo Martin-Brualla. 2021. Nerfies: Deformable Neural Radiance Fields. In ICCV. 5865--5874."},{"unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017).","key":"e_1_3_2_1_28_1"},{"doi-asserted-by":"crossref","unstructured":"Sida Peng Junting Dong QianqianWang Shangzhan Zhang Qing Shuai Xiaowei Zhou and Hujun Bao. 2021. Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies. In ICCV. 14314--14323.","key":"e_1_3_2_1_29_1","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"e_1_3_2_1_30_1","volume-title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans. In CVPR. 9054--9063.","author":"Peng Sida","year":"2021","unstructured":"Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, and Xiaowei Zhou. 2021. Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans. In CVPR. 9054--9063."},{"doi-asserted-by":"crossref","unstructured":"Albert Pumarola Enric Corona Gerard Pons-Moll and Francesc Moreno-Noguer. 2021. D-Nerf: Neural Radiance Fields for Dynamic Scenes. In CVPR. 10318--10327.","key":"e_1_3_2_1_31_1","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"e_1_3_2_1_32_1","volume-title":"Anr: Articulated Neural Rendering for Virtual Avatars. In CVPR. 3722--3731.","author":"Raj Amit","year":"2021","unstructured":"Amit Raj, Julian Tanke, James Hays, Minh Vo, Carsten Stoll, and Christoph Lassner. 2021. Anr: Articulated Neural Rendering for Virtual Avatars. In CVPR. 3722--3731."},{"key":"e_1_3_2_1_33_1","volume-title":"Pva: Pixel-aligned Volumetric Avatars. arXiv preprint arXiv:2101.02697","author":"Raj Amit","year":"2021","unstructured":"Amit Raj, Michael Zollhoefer, Tomas Simon, Jason Saragih, Shunsuke Saito, James Hays, and Stephen Lombardi. 2021. Pva: Pixel-aligned Volumetric Avatars. arXiv preprint arXiv:2101.02697 (2021). arXiv:2101.02697"},{"key":"e_1_3_2_1_34_1","volume-title":"Pifu: Pixel-aligned Implicit Function for High-Resolution Clothed Human Digitization. In ICCV. 2304--2314.","author":"Saito Shunsuke","year":"2019","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. 2304--2314."},{"key":"e_1_3_2_1_35_1","volume-title":"Pifuhd: Multi-level Pixel-Aligned Implicit Function for High-Resolution 3d Human Digitization. In CVPR. 84--93.","author":"Saito Shunsuke","year":"2020","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. 84--93."},{"unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR.","key":"e_1_3_2_1_36_1"},{"key":"e_1_3_2_1_37_1","volume-title":"Scene Representation Networks: Continuous 3d-Structure-Aware Neural Scene Representations. Advances in Neural Information Processing Systems 32","author":"Sitzmann Vincent","year":"2019","unstructured":"Vincent Sitzmann, Michael Zollh\u00f6fer, and Gordon Wetzstein. 2019. Scene Representation Networks: Continuous 3d-Structure-Aware Neural Scene Representations. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_38_1","first-page":"12278","article-title":"A-Nerf: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose","volume":"34","author":"Su Shih-Yang","year":"2021","unstructured":"Shih-Yang Su, Frank Yu, Michael Zollh\u00f6fer, and Helge Rhodin. 2021. A-Nerf: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose. Advances in Neural Information Processing Systems 34 (2021), 12278--12291.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","first-page":"7537","article-title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","volume":"33","author":"Tancik Matthew","year":"2020","unstructured":"Matthew Tancik, Pratul Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan Barron, and Ren Ng. 2020. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains. Advances in Neural Information Processing Systems 33 (2020), 7537--7547.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"crossref","unstructured":"Edgar Tretschk Ayush Tewari Vladislav Golyanik Michael Zollh\u00f6fer Christoph Lassner and Christian Theobalt. 2021. Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene from Monocular Video. In ICCV. 12959--12970.","key":"e_1_3_2_1_40_1","DOI":"10.1109\/ICCV48922.2021.01272"},{"key":"e_1_3_2_1_41_1","volume-title":"Grf: Learning a General Radiance Field for 3d Representation and Rendering. In ICCV. 15182--15192.","author":"Trevithick Alex","year":"2021","unstructured":"Alex Trevithick and Bo Yang. 2021. Grf: Learning a General Radiance Field for 3d Representation and Rendering. In ICCV. 15182--15192."},{"doi-asserted-by":"crossref","unstructured":"Qianqian Wang Zhicheng Wang Kyle Genova Pratul P. Srinivasan Howard Zhou Jonathan T. Barron Ricardo Martin-Brualla Noah Snavely and Thomas Funkhouser. 2021. IBRnet: Learning Multi-View Image-Based Rendering. In CVPR. 4690--4699.","key":"e_1_3_2_1_42_1","DOI":"10.1109\/CVPR46437.2021.00466"},{"unstructured":"Yiming Wang Qingzhe Gao Libin Liu Lingjie Liu Christian Theobalt and Baoquan Chen. 2022. Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors. arXiv:2208.11905 [cs]","key":"e_1_3_2_1_43_1"},{"key":"e_1_3_2_1_44_1","volume-title":"Humannerf: Free-viewpoint Rendering of Moving People from Monocular Video. In CVPR. 16210--16220.","author":"Weng Chung-Yi","year":"2022","unstructured":"Chung-Yi Weng, Brian Curless, Pratul P. Srinivasan, Jonathan T. Barron, and Ira Kemelmacher-Shlizerman. 2022. Humannerf: Free-viewpoint Rendering of Moving People from Monocular Video. In CVPR. 16210--16220."},{"unstructured":"Minye Wu Yuehao Wang Qiang Hu and Jingyi Yu. 2020. Multi-View Neural Human Rendering. In CVPR. 1682--1691.","key":"e_1_3_2_1_45_1"},{"doi-asserted-by":"crossref","unstructured":"Ze Yang Shenlong Wang Sivabalan Manivasagam Zeng Huang Wei-Chiu Ma Xinchen Yan Ersin Yumer and Raquel Urtasun. 2021. S3: Neural Shape Skeleton and Skinning Fields for 3d Human Modeling. In CVPR. 13284--13293.","key":"e_1_3_2_1_46_1","DOI":"10.1109\/CVPR46437.2021.01308"},{"key":"e_1_3_2_1_47_1","first-page":"4805","article-title":"Volume Rendering of Neural Implicit Surfaces","volume":"34","author":"Yariv Lior","year":"2021","unstructured":"Lior Yariv, Jiatao Gu, Yoni Kasten, and Yaron Lipman. 2021. Volume Rendering of Neural Implicit Surfaces. Advances in Neural Information Processing Systems 34 (2021), 4805--4815.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_48_1","volume-title":"Pixelnerf: Neural Radiance Fields from One or Few Images. In CVPR. 4578--4587.","author":"Yu Alex","year":"2021","unstructured":"Alex Yu, Vickie Ye, Matthew Tancik, and Angjoo Kanazawa. 2021. Pixelnerf: Neural Radiance Fields from One or Few Images. In CVPR. 4578--4587."},{"key":"e_1_3_2_1_49_1","article-title":"Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things","volume":"8","author":"Zhang Jing","year":"2020","unstructured":"Jing Zhang and Dacheng Tao. 2020. Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things. IEEE Internet of Things Journal 8, 10 (2020), 7789?7817.","journal-title":"IEEE Internet of Things Journal"},{"doi-asserted-by":"crossref","unstructured":"Fuqiang Zhao Wei Yang Jiakai Zhang Pei Lin Yingliang Zhang Jingyi Yu and Lan Xu. 2022. HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs. In CVPR. 7743--7753.","key":"e_1_3_2_1_50_1","DOI":"10.1109\/CVPR52688.2022.00759"},{"volume-title":"Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces. In 2022 International Conference on 3D Vision (3DV). IEEE Computer Society","author":"Zhi Y.","unstructured":"Y. Zhi, S. Qian, X. Yan, and S. Gao. 2022. Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces. In 2022 International Conference on 3D Vision (3DV). IEEE Computer Society, Los Alamitos, CA, USA, 1--10.","key":"e_1_3_2_1_51_1"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '23","name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612058","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:02:03Z","timestamp":1755820923000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":51,"alternative-id":["10.1145\/3581783.3612058","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612058","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}