{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T16:59:37Z","timestamp":1767977977578,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":58,"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":"the 111 project under Grant B07022 and Sheitc No.150633"},{"name":"National Key RD Project of China","award":["2019YFB1802701"],"award-info":[{"award-number":["2019YFB1802701"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102024, 62331014"],"award-info":[{"award-number":["62102024, 62331014"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Fundamental Research Funds for the Central Universities"},{"name":"the Shanghai Key Laboratory of Digital Media Processing and Transmissions"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680970","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"3974-3983","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Rate-aware Compression for NeRF-based Volumetric Video"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1728-4754","authenticated-orcid":false,"given":"Zhiyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-0090","authenticated-orcid":false,"given":"Guo","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0612-6363","authenticated-orcid":false,"given":"Huanxiong","family":"Liang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5364-7427","authenticated-orcid":false,"given":"Zhengxue","family":"Cheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9772-3293","authenticated-orcid":false,"given":"Anni","family":"Tang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7124-5182","authenticated-orcid":false,"given":"Li","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of Intl. Conf. on Learning Representations (ICLR).","author":"Ball\u00e9 J.","unstructured":"J. Ball\u00e9, Valero Laparra, and Eero P. Simoncelli. 2018. End-to-End Optimized Image Compression. In Proceedings of Intl. Conf. on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_2_1","volume-title":"Calculation of average PSNR differences between RD-curves. ITU SG16 Doc. VCEG-M33","author":"Bjontegaard Gisle","year":"2001","unstructured":"Gisle Bjontegaard. 2001. Calculation of average PSNR differences between RD-curves. ITU SG16 Doc. VCEG-M33 (2001)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3062590"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592135","article-title":"Dictionary fields: Learning a neural basis decomposition","volume":"42","author":"Chen Anpei","year":"2023","unstructured":"Anpei Chen, Zexiang Xu, Xinyue Wei, Siyu Tang, Hao Su, and Andreas Geiger. 2023. Dictionary fields: Learning a neural basis decomposition. ACM Transactions on Graphics (TOG), Vol. 42, 4 (2023), 1--12.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01406"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555383"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01606"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2020.12"},{"key":"e_1_3_2_1_16_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Guo Haoyu","year":"2024","unstructured":"Haoyu Guo, Sida Peng, Yunzhi Yan, Linzhan Mou, Yujun Shen, Hujun Bao, and Xiaowei Zhou. 2024. Compact neural volumetric video representations with dynamic codebooks. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592415"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00294"},{"key":"e_1_3_2_1_19_1","volume-title":"Jonathan Richard Schwarz, and Emilien Dupont","author":"Kim Hyunjik","year":"2024","unstructured":"Hyunjik Kim, Matthias Bauer, Lucas Theis, Jonathan Richard Schwarz, and Emilien Dupont. 2024. C3: High-performance and low-complexity neural compression from a single image or video. (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimization. arXiv preprint arXiv:2311.14208","author":"Lee Soonbin","year":"2023","unstructured":"Soonbin Lee, Fangwen Shu, Yago Sanchez, Thomas Schierl, and Cornelius Hellge. 2023. ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimization. arXiv preprint arXiv:2311.14208 (2023)."},{"key":"e_1_3_2_1_21_1","first-page":"18114","article-title":"Deep contextual video compression","volume":"34","author":"Li Jiahao","year":"2021","unstructured":"Jiahao Li, Bin Li, and Yan Lu. 2021. Deep contextual video compression. Advances in Neural Information Processing Systems, Vol. 34 (2021), 18114--18125.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"e_1_3_2_1_23_1","unstructured":"Jiahao Li Bin Li and Yan Lu. 2024. Neural Video Compression with Feature Modulatio. (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00411"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02010"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"e_1_3_2_1_28_1","first-page":"36762","article-title":"Devrf: Fast deformable voxel radiance fields for dynamic scenes","volume":"35","author":"Liu Jia-Wei","year":"2022","unstructured":"Jia-Wei Liu, Yan-Pei Cao, Weijia Mao, Wenqiao Zhang, David Junhao Zhang, Jussi Keppo, Ying Shan, Xiaohu Qie, and Mike Zheng Shou. 2022. Devrf: Fast deformable voxel radiance fields for dynamic scenes. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36762--36775.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"DVC: An End-to-end Deep Video Compression Framework.","author":"Lu Guo","year":"2019","unstructured":"Guo Lu, Wanli Ouyang, Dong Xu, Xiaoyun Zhang, Chunlei Cai, and Zhiyong Gao. 2019. DVC: An End-to-end Deep Video Compression Framework. (2019)."},{"key":"e_1_3_2_1_30_1","volume-title":"CAwa-NeRF: Instant Learning of Compression-Aware NeRF Features. arXiv preprint arXiv:2310.14695","author":"Mahmoud Omnia","year":"2023","unstructured":"Omnia Mahmoud, Th\u00e9o Ladune, and Matthieu Gendrin. 2023. CAwa-NeRF: Instant Learning of Compression-Aware NeRF Features. arXiv preprint arXiv:2310.14695 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. Institution of Electronic and Radio Engineers International Conference on Video and Data Recording","volume":"2","author":"Martin G Nigel N","year":"1979","unstructured":"G Nigel N Martin. 1979. Range encoding: an algorithm for removing redundancy from a digitised message. In Proc. Institution of Electronic and Radio Engineers International Conference on Video and Data Recording, Vol. 2."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_33_1","volume-title":"Joint autoregressive and hierarchical priors for learned image compression. Advances in neural information processing systems","author":"Minnen David","year":"2018","unstructured":"David Minnen, Johannes Ball\u00e9, and George D Toderici. 2018. Joint autoregressive and hierarchical priors for learned image compression. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00598"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01981"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2018.2885981"},{"key":"e_1_3_2_1_40_1","volume-title":"VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision","author":"Sheng Xihua","year":"2024","unstructured":"Xihua Sheng, Li Li, Dong Liu, and Houqiang Li. 2024. VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Binary Radiance Fields. arXiv preprint arXiv:2306.07581","author":"Shin Seungjoo","year":"2023","unstructured":"Seungjoo Shin and Jaesik Park. 2023. Binary Radiance Fields. arXiv preprint arXiv:2306.07581 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/79.952804"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01381"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"e_1_3_2_1_45_1","volume-title":"Integrated circuit and systems, algorithms and architectures.","author":"Sze Vivienne","unstructured":"Vivienne Sze, Madhukar Budagavi, and Gary J Sullivan. 2014. High efficiency video coding (HEVC). In Integrated circuit and systems, algorithms and architectures. Vol. 39. Springer, 40."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530727"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00016"},{"key":"e_1_3_2_1_49_1","volume-title":"VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams. arXiv preprint arXiv:2312.01407","author":"Wang Liao","year":"2023","unstructured":"Liao Wang, Kaixin Yao, Chengcheng Guo, Zhirui Zhang, Qiang Hu, Jingyi Yu, Lan Xu, and Minye Wu. 2023. VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams. arXiv preprint arXiv:2312.01407 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01316"},{"key":"e_1_3_2_1_51_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_52_1","volume-title":"TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video. arXiv preprint arXiv:2312.06713","author":"Wu Minye","year":"2023","unstructured":"Minye Wu, Zehao Wang, Georgios Kouros, and Tinne Tuytelaars. 2023. TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video. arXiv preprint arXiv:2312.06713 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00930"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3212780"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_56_1","volume-title":"Efficient Dynamic-NeRF Based Volumetric Video Coding with Rate Distortion Optimization. arXiv preprint arXiv:2402.01380","author":"Zhang Zhiyu","year":"2024","unstructured":"Zhiyu Zhang, Guo Lu, Huanxiong Liang, Anni Tang, Qiang Hu, and Li Song. 2024. Efficient Dynamic-NeRF Based Volumetric Video Coding with Rate Distortion Optimization. arXiv preprint arXiv:2402.01380 (2024)."},{"key":"e_1_3_2_1_57_1","volume-title":"High-Fidelity Free-View Talking Head Synthesis for Low-Bandwidth Video Conference. In 2023 IEEE International Conference on Visual Communications and Image Processing (VCIP). IEEE, 1--5.","author":"Zhang Zhiyu","year":"2023","unstructured":"Zhiyu Zhang, Anni Tang, Chen Zhu, Guo Lu, Rong Xie, and Li Song. 2023. High-Fidelity Free-View Talking Head Synthesis for Low-Bandwidth Video Conference. In 2023 IEEE International Conference on Visual Communications and Image Processing (VCIP). IEEE, 1--5."},{"key":"e_1_3_2_1_58_1","volume-title":"JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compression. arXiv preprint arXiv:2405.14452","author":"Zheng Zihan","year":"2024","unstructured":"Zihan Zheng, Houqiang Zhong, Qiang Hu, Xiaoyun Zhang, Li Song, Ya Zhang, and Yanfeng Wang. 2024. JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compression. arXiv preprint arXiv:2405.14452 (2024)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680970","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:35Z","timestamp":1750295855000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680970"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":58,"alternative-id":["10.1145\/3664647.3680970","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680970","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"}}]}}