{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T02:21:52Z","timestamp":1777515712183,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T00:00:00Z","timestamp":1694304000000},"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":[[2023,9,10]]},"DOI":"10.1145\/3609395.3610593","type":"proceedings-article","created":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T21:19:55Z","timestamp":1695763195000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Mobile Volumetric Video Streaming System through Implicit Neural Representation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4494-765X","authenticated-orcid":false,"given":"Junhua","family":"Liu","sequence":"first","affiliation":[{"name":"FNii, CUHK-Shenzhen, Shenzhen, China"},{"name":"Sensetime Research, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4190-6418","authenticated-orcid":false,"given":"Yuanyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Sensetime Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3594-2658","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5888-0303","authenticated-orcid":false,"given":"Yufeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2608-775X","authenticated-orcid":false,"given":"Shuguang","family":"Cui","sequence":"additional","affiliation":[{"name":"SSE, CUHK-Shenzhen, Shenzhen, China"},{"name":"FNii, CUHK-Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-045X","authenticated-orcid":false,"given":"Fangxin","family":"Wang","sequence":"additional","affiliation":[{"name":"SSE, CUHK-Shenzhen, Shenzhen, China"},{"name":"FNii, CUHK-Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,9,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"8i voxelized full bodies-a voxelized point cloud dataset. http:\/\/plenodb.jpeg.org\/pc\/8ilabs\/.  8i voxelized full bodies-a voxelized point cloud dataset. http:\/\/plenodb.jpeg.org\/pc\/8ilabs\/."},{"key":"e_1_3_2_1_2_1","unstructured":"Blender.  Blender."},{"key":"e_1_3_2_1_3_1","unstructured":"Jpeg pleno database:microsoft voxelized upper bodies-a voxelized point cloud dataset. https:\/\/plenodb.jpeg.org\/pc\/microsoft.  Jpeg pleno database:microsoft voxelized upper bodies-a voxelized point cloud dataset. https:\/\/plenodb.jpeg.org\/pc\/microsoft."},{"key":"e_1_3_2_1_4_1","unstructured":"Lepcc. https:\/\/github.com\/Esri\/lepcc.  Lepcc. https:\/\/github.com\/Esri\/lepcc."},{"key":"e_1_3_2_1_5_1","unstructured":"Point cloud library. http:\/\/pointclouds.org.  Point cloud library. http:\/\/pointclouds.org."},{"key":"e_1_3_2_1_6_1","unstructured":"Point cloud visualizer addon. https:\/\/www.blendermarket.com\/products\/pcv.  Point cloud visualizer addon. https:\/\/www.blendermarket.com\/products\/pcv."},{"key":"e_1_3_2_1_7_1","unstructured":"Stop motion obj addon. https:\/\/github.com\/neverhood311\/Stop-motion-OBJ.  Stop motion obj addon. https:\/\/github.com\/neverhood311\/Stop-motion-OBJ."},{"key":"e_1_3_2_1_8_1","volume-title":"https:\/\/google.github.io\/draco","year":"2018","unstructured":"Draco 3d. https:\/\/google.github.io\/draco , 2018 . Draco 3d. https:\/\/google.github.io\/draco, 2018."},{"key":"e_1_3_2_1_9_1","volume-title":"An introductory study on time series modeling and forecasting. arXiv preprint arXiv:1302.6613","author":"Adhikari R.","year":"2013","unstructured":"R. Adhikari and R. K. Agrawal . An introductory study on time series modeling and forecasting. arXiv preprint arXiv:1302.6613 , 2013 . R. Adhikari and R. K. Agrawal. An introductory study on time series modeling and forecasting. arXiv preprint arXiv:1302.6613, 2013."},{"key":"e_1_3_2_1_10_1","first-page":"16569","volume-title":"Proceedings of the IEEE\/CVF CVPR","author":"Chen Z.","year":"2023","unstructured":"Z. Chen , T. Funkhouser , P. Hedman , and A. Tagliasacchi . Mobilenerf: Exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures . In Proceedings of the IEEE\/CVF CVPR , pages 16569 -- 16578 , 2023 . Z. Chen, T. Funkhouser, P. Hedman, and A. Tagliasacchi. Mobilenerf: Exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures. In Proceedings of the IEEE\/CVF CVPR, pages 16569--16578, 2023."},{"key":"e_1_3_2_1_11_1","volume-title":"Deep learning on implicit neural representations of shapes. arXiv preprint arXiv:2302.05438","author":"De Luigi L.","year":"2023","unstructured":"L. De Luigi , A. Cardace , R. Spezialetti , P. Z. Ramirez , S. Salti , and L. Di Stefano . Deep learning on implicit neural representations of shapes. arXiv preprint arXiv:2302.05438 , 2023 . L. De Luigi, A. Cardace, R. Spezialetti, P. Z. Ramirez, S. Salti, and L. Di Stefano. Deep learning on implicit neural representations of shapes. arXiv preprint arXiv:2302.05438, 2023."},{"key":"e_1_3_2_1_12_1","volume-title":"Sparf: Large-scale learning of 3d sparse radiance fields from few input images. arXiv preprint arXiv:2212.09100","author":"Hamdi A.","year":"2022","unstructured":"A. Hamdi , B. Ghanem , and M. Nie\u00dfner . Sparf: Large-scale learning of 3d sparse radiance fields from few input images. arXiv preprint arXiv:2212.09100 , 2022 . A. Hamdi, B. Ghanem, and M. Nie\u00dfner. Sparf: Large-scale learning of 3d sparse radiance fields from few input images. arXiv preprint arXiv:2212.09100, 2022."},{"key":"e_1_3_2_1_13_1","first-page":"1","volume-title":"Proceedings of the 26th annual international conference on mobile computing and networking","author":"Han B.","year":"2020","unstructured":"B. Han , Y. Liu , and F. Qian . Vivo: Visibility-aware mobile volumetric video streaming . In Proceedings of the 26th annual international conference on mobile computing and networking , pages 1 -- 13 , 2020 . B. Han, Y. Liu, and F. Qian. Vivo: Visibility-aware mobile volumetric video streaming. In Proceedings of the 26th annual international conference on mobile computing and networking, pages 1--13, 2020."},{"key":"e_1_3_2_1_14_1","first-page":"5875","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Hedman P.","year":"2021","unstructured":"P. Hedman , P. P. Srinivasan , B. Mildenhall , J. T. Barron , and P. Debevec . Baking neural radiance fields for real-time view synthesis . In Proceedings of the IEEE\/CVF International Conference on Computer Vision , pages 5875 -- 5884 , 2021 . P. Hedman, P. P. Srinivasan, B. Mildenhall, J. T. Barron, and P. Debevec. Baking neural radiance fields for real-time view synthesis. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pages 5875--5884, 2021."},{"key":"e_1_3_2_1_15_1","first-page":"1","volume-title":"Science China Information Sciences","author":"Hu S.-M.","year":"2020","unstructured":"S.-M. Hu , D. Liang , G.-Y. Yang , G.-W. Yang , and W.-Y. Zhou . Jittor : a novel deep learning framework with meta-operators and unified graph execution . Science China Information Sciences , pages 1 -- 21 , 2020 . S.-M. Hu, D. Liang, G.-Y. Yang, G.-W. Yang, and W.-Y. Zhou. Jittor: a novel deep learning framework with meta-operators and unified graph execution. Science China Information Sciences, pages 1--21, 2020."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/VRW55335.2022.00151","volume-title":"2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)","author":"Jin Y.","year":"2022","unstructured":"Y. Jin , J. Liu , and F. Wang . Ebublio: Edge assisted multi-user 360-degree video streaming . In 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) , pages 600 -- 601 . IEEE, 2022 . Y. Jin, J. Liu, and F. Wang. Ebublio: Edge assisted multi-user 360-degree video streaming. In 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pages 600--601. IEEE, 2022."},{"key":"e_1_3_2_1_17_1","first-page":"1","volume-title":"Proceedings of the 26th Annual International Conference on Mobile Computing and Networking","author":"Lee K.","year":"2020","unstructured":"K. Lee , J. Yi , Y. Lee , S. Choi , and Y. M. Kim . Groot: a real-time streaming system of high-fidelity volumetric videos . In Proceedings of the 26th Annual International Conference on Mobile Computing and Networking , pages 1 -- 14 , 2020 . K. Lee, J. Yi, Y. Lee, S. Choi, and Y. M. Kim. Groot: a real-time streaming system of high-fidelity volumetric videos. In Proceedings of the 26th Annual International Conference on Mobile Computing and Networking, pages 1--14, 2020."},{"key":"e_1_3_2_1_18_1","article-title":"Optimal volumetric video streaming with hybrid saliency based tiling","author":"Li J.","year":"2022","unstructured":"J. Li , C. Zhang , Z. Liu , R. Hong , and H. Hu . Optimal volumetric video streaming with hybrid saliency based tiling . IEEE Transactions on Multimedia , 2022 . J. Li, C. Zhang, Z. Liu, R. Hong, and H. Hu. Optimal volumetric video streaming with hybrid saliency based tiling. IEEE Transactions on Multimedia, 2022.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1145\/3495243.3517027","volume-title":"Proceedings of the 28th Annual International Conference on Mobile Computing And Networking","author":"Liu Y.","year":"2022","unstructured":"Y. Liu , B. Han , F. Qian , A. Narayanan , and Z.-L. Zhang . Vues : practical mobile volumetric video streaming through multiview transcoding . In Proceedings of the 28th Annual International Conference on Mobile Computing And Networking , pages 514 -- 527 , 2022 . Y. Liu, B. Han, F. Qian, A. Narayanan, and Z.-L. Zhang. Vues: practical mobile volumetric video streaming through multiview transcoding. In Proceedings of the 28th Annual International Conference on Mobile Computing And Networking, pages 514--527, 2022."},{"key":"e_1_3_2_1_20_1","volume-title":"Neural volumes: Learning dynamic renderable volumes from images. arXiv preprint arXiv:1906.07751","author":"Lombardi S.","year":"2019","unstructured":"S. Lombardi , T. Simon , J. Saragih , G. Schwartz , A. Lehrmann , and Y. Sheikh . Neural volumes: Learning dynamic renderable volumes from images. arXiv preprint arXiv:1906.07751 , 2019 . S. Lombardi, T. Simon, J. Saragih, G. Schwartz, A. Lehrmann, and Y. Sheikh. Neural volumes: Learning dynamic renderable volumes from images. arXiv preprint arXiv:1906.07751, 2019."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_1_22_1","volume-title":"Local light field fusion: Practical view synthesis with prescriptive sampling guidelines. ACM Transactions on Graphics (TOG), 38(4):1--14","author":"Mildenhall B.","year":"2019","unstructured":"B. Mildenhall , P. P. Srinivasan , R. Ortiz-Cayon , N. K. Kalantari , R. Ramamoorthi , R. Ng , and A. Kar . Local light field fusion: Practical view synthesis with prescriptive sampling guidelines. ACM Transactions on Graphics (TOG), 38(4):1--14 , 2019 . B. Mildenhall, P. P. Srinivasan, R. Ortiz-Cayon, N. K. Kalantari, R. Ramamoorthi, R. Ng, and A. Kar. Local light field fusion: Practical view synthesis with prescriptive sampling guidelines. ACM Transactions on Graphics (TOG), 38(4):1--14, 2019."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_1_24_1","first-page":"1928","volume-title":"International conference on machine learning","author":"Mnih V.","year":"2016","unstructured":"V. Mnih , A. P. Badia , M. Mirza , A. Graves , T. Lillicrap , T. Harley , D. Silver , and K. Kavukcuoglu . Asynchronous methods for deep reinforcement learning . In International conference on machine learning , pages 1928 -- 1937 . PMLR, 2016 . V. Mnih, A. P. Badia, M. Mirza, A. Graves, T. Lillicrap, T. Harley, D. Silver, and K. Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In International conference on machine learning, pages 1928--1937. PMLR, 2016."},{"key":"e_1_3_2_1_25_1","volume-title":"Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (ToG), 41(4):1--15","author":"M\u00fcller T.","year":"2022","unstructured":"T. M\u00fcller , A. Evans , C. Schied , and A. Keller . Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (ToG), 41(4):1--15 , 2022 . T. M\u00fcller, A. Evans, C. Schied, and A. Keller. Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (ToG), 41(4):1--15, 2022."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2343483.2343488"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2898622"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1145\/3458305.3478452","volume-title":"Proceedings of the 12th ACM Multimedia Systems Conference","author":"Reimat I.","year":"2021","unstructured":"I. Reimat , E. Alexiou , J. Jansen , I. Viola , S. Subramanyam , and P. Cesar . Cwipc-sxr: Point cloud dynamic human dataset for social xr . In Proceedings of the 12th ACM Multimedia Systems Conference , pages 300 -- 306 , 2021 . I. Reimat, E. Alexiou, J. Jansen, I. Viola, S. Subramanyam, and P. Cesar. Cwipc-sxr: Point cloud dynamic human dataset for social xr. In Proceedings of the 12th ACM Multimedia Systems Conference, pages 300--306, 2021."},{"key":"e_1_3_2_1_29_1","volume-title":"Nerf-slam: Real-time dense monocular slam with neural radiance fields. arXiv preprint arXiv:2210.13641","author":"Rosinol A.","year":"2022","unstructured":"A. Rosinol , J. J. Leonard , and L. Carlone . Nerf-slam: Real-time dense monocular slam with neural radiance fields. arXiv preprint arXiv:2210.13641 , 2022 . A. Rosinol, J. J. Leonard, and L. Carlone. Nerf-slam: Real-time dense monocular slam with neural radiance fields. arXiv preprint arXiv:2210.13641, 2022."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530727"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530727"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419185"},{"key":"e_1_3_2_1_33_1","first-page":"137","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation","author":"Zhang A.","year":"2022","unstructured":"A. Zhang , C. Wang , B. Han , and F. Qian . Yuzu: Neural-enhanced volumetric video streaming . In 19th USENIX Symposium on Networked Systems Design and Implementation , pages 137 -- 154 , 2022 . A. Zhang, C. Wang, B. Han, and F. Qian. Yuzu: Neural-enhanced volumetric video streaming. In 19th USENIX Symposium on Networked Systems Design and Implementation, pages 137--154, 2022."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_35_1","volume-title":"Nicer-slam: Neural implicit scene encoding for rgb slam. arXiv preprint arXiv:2302.03594","author":"Zhu Z.","year":"2023","unstructured":"Z. Zhu , S. Peng , V. Larsson , Z. Cui , M. R. Oswald , A. Geiger , and M. Pollefeys . Nicer-slam: Neural implicit scene encoding for rgb slam. arXiv preprint arXiv:2302.03594 , 2023 . Z. Zhu, S. Peng, V. Larsson, Z. Cui, M. R. Oswald, A. Geiger, and M. Pollefeys. Nicer-slam: Neural implicit scene encoding for rgb slam. arXiv preprint arXiv:2302.03594, 2023."}],"event":{"name":"EMS '23: 2023 Workshop on Emerging Multimedia Systems","location":"New York NY USA","acronym":"EMS '23","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the 2023 Workshop on Emerging Multimedia Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3609395.3610593","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3609395.3610593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:23Z","timestamp":1750178783000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3609395.3610593"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,10]]},"references-count":35,"alternative-id":["10.1145\/3609395.3610593","10.1145\/3609395"],"URL":"https:\/\/doi.org\/10.1145\/3609395.3610593","relation":{},"subject":[],"published":{"date-parts":[[2023,9,10]]},"assertion":[{"value":"2023-09-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}