{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:42:25Z","timestamp":1773193345190,"version":"3.50.1"},"reference-count":79,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2022YFB4501400"],"award-info":[{"award-number":["2022YFB4501400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62072297 and 62222210"],"award-info":[{"award-number":["62072297 and 62222210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2024,12,31]]},"abstract":"<jats:p>\n            Neural Radiance Field (NeRF) has emerged as a promising alternative for photorealistic rendering. Despite recent algorithmic advancements, achieving real-time performance on today\u2019s resource-constrained devices remains challenging. In this article, we identify the primary bottlenecks in current NeRF algorithms and introduce a unified algorithm-architecture co-design,\n            <jats:sc>Potamoi<\/jats:sc>\n            , designed to accommodate various NeRF algorithms. Specifically, we introduce a runtime system featuring a plug-and-play algorithm,\n            <jats:sc>SpaRW<\/jats:sc>\n            , which significantly reduces the per-frame computational workload and alleviates compute inefficiencies. Furthermore, our unified streaming pipeline coupled with customized hardware support effectively tames both SRAM and DRAM inefficiencies by minimizing repetitive DRAM access and completely eliminating SRAM bank conflicts. When evaluated against a baseline utilizing a dedicated DNN accelerator, our framework demonstrates a speedup and energy reduction of 53.1\u00d7 and 67.7\u00d7, respectively, all while maintaining high visual quality with less than a 1.0 dB reduction in peak signal-to-noise ratio.\n          <\/jats:p>","DOI":"10.1145\/3689340","type":"journal-article","created":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T23:31:39Z","timestamp":1724283099000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Potamoi: Accelerating Neural Rendering via a Unified Streaming Architecture"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2192-5737","authenticated-orcid":false,"given":"Yu","family":"Feng","sequence":"first","affiliation":[{"name":"John Hopcropt Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3537-4857","authenticated-orcid":false,"given":"Weikai","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0874-0682","authenticated-orcid":false,"given":"Zihan","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5660-5493","authenticated-orcid":false,"given":"Jingwen","family":"Leng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Shanghai Jiao Tong University, Shanghai, China and Shanghai Qi Zhi Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2302","authenticated-orcid":false,"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Computer Science, Shanghai Jiao Tong University, Shanghai, China and Shanghai Qi Zhi Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1561-5329","authenticated-orcid":false,"given":"Han","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4372-7851","authenticated-orcid":false,"given":"Xiaofeng","family":"Hou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8211-2812","authenticated-orcid":false,"given":"Jieru","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2802-0578","authenticated-orcid":false,"given":"Yuhao","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919636"},{"key":"e_1_3_3_3_2","article-title":"Agisoft Metashape","year":"2024","unstructured":"Agisoft. 2024. Agisoft Metashape. Retrieved August 27, 2024 from https:\/\/www.agisoft.com\/","journal-title":"https:\/\/www.agisoft.com\/"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/1921479.1921497"},{"key":"e_1_3_3_5_2","unstructured":"Apple. 2021. Apple A15 Die Shot and Annotation\u2014IP Block Area Analysis. Retrieved August 27 2024 from https:\/\/www.semianalysis.com\/p\/apple-a15-die-shot-and-annotation"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00255"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_3_8_2","unstructured":"Parhami Behrooz. 2000. Computer Arithmetic: Algorithms and Hardware Designs. Oxford University Press 19 (2000) 512583\u2013512585."},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03073.x"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906418"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00051"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"e_1_3_3_13_2","article-title":"A survey on 3D Gaussian splatting","author":"Chen Guikun","year":"2024","unstructured":"Guikun Chen and Wenguan Wang. 2024. A survey on 3D Gaussian splatting. arXiv preprint arXiv:2401.03890 (2024).","journal-title":"arXiv preprint arXiv:2401.03890"},{"key":"e_1_3_3_14_2","first-page":"578","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201918)","author":"Chen Tianqi","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An automated end-to-end optimizing compiler for deep learning. In Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201918). 578\u2013594."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01590"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3104067"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527395"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341071"},{"key":"e_1_3_3_19_2","article-title":"Cicero: Addressing algorithmic and architectural bottlenecks in neural rendering by radiance warping and memory optimizations","author":"Feng Yu","year":"2024","unstructured":"Yu Feng, Zihan Liu, Jingwen Leng, Minyi Guo, and Yuhao Zhu. 2024. Cicero: Addressing algorithmic and architectural bottlenecks in neural rendering by radiance warping and memory optimizations. arXiv preprint arXiv:2404.11852 (2024).","journal-title":"arXiv preprint arXiv:2404.11852"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00087"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358253"},{"key":"e_1_3_3_22_2","volume-title":"Computer Vision: A Modern Approach","author":"Forsyth David A.","year":"2002","unstructured":"David A. Forsyth and Jean Ponce. 2002. Computer Vision: A Modern Approach. Prentice Hall."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589109"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508377"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596760"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/RT.2008.4634622"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000112"},{"key":"e_1_3_3_28_2","article-title":"MetaVRain: A mobile neural 3-D rendering processor with bundle-frame-familiarity-based NeRF acceleration and hybrid DNN computing","author":"Han Donghyeon","year":"2023","unstructured":"Donghyeon Han, Junha Ryu, Sangyeob Kim, Sangjin Kim, Jongjun Park, and Hoi-Jun Yoo. 2023. MetaVRain: A mobile neural 3-D rendering processor with bundle-frame-familiarity-based NeRF acceleration and hybrid DNN computing. IEEE Journal of Solid-State Circuits. Published Online, July 13, 2023.","journal-title":"IEEE Journal of Solid-State Circuits."},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00582"},{"key":"e_1_3_3_30_2","first-page":"Article 233, 13","article-title":"QuadStream: A quad-Bbased scene streaming architecture for novel viewpoint reconstruction","author":"Hladky Jozef","year":"2022","unstructured":"Jozef Hladky, Michael Stengel, Nicholas Vining, Bernhard Kerbl, and Hans-Peter Seidel. 2022. QuadStream: A quad-Bbased scene streaming architecture for novel viewpoint reconstruction. ACM Transactions on Graphics 41, 6 (2022), Article 233, 13 pages.","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01256"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.1993.274942"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_35_2","volume-title":"Programming Massively Parallel Processors: A Hands-On Approach","author":"Kirk David B.","year":"2016","unstructured":"David B. Kirk and W. Hwu Wen-Mei. 2016. Programming Massively Parallel Processors: A Hands-On Approach. Morgan Kaufmann."},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589056"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651385"},{"key":"e_1_3_3_39_2","article-title":"Compact 3D Gaussian representation for radiance field","author":"Lee Joo Chan","year":"2023","unstructured":"Joo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko, and Eunbyung Park. 2023. Compact 3D Gaussian representation for radiance field. arXiv preprint arXiv:2311.13681 (2023).","journal-title":"arXiv preprint arXiv:2311.13681"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322264"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/38.511"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596759"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549380"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589115"},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731584"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640360"},{"key":"e_1_3_3_47_2","unstructured":"Micron. 2014. Micron 178-Ball Single-Channel Mobile LPDDR3 SDRAM Features. https:\/\/www.farnell.com\/datasheets\/3761299.pdf"},{"key":"e_1_3_3_48_2","unstructured":"Micron. 2022. Micron System Power Calculators. Retrieved August 27 2024 from https:\/\/www.micron.com\/support\/tools-and-utilities\/power-calc"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589085"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275087"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2003.1159614"},{"key":"e_1_3_3_54_2","unstructured":"NVIDIA. 2018. NVIDIA Reveals Xavier SOC Details. Retrieved August 27 2024 from https:\/\/www.forbes.com\/sites\/moorinsights\/2018\/08\/24\/nvidia-reveals-xavier-soc-details\/amp\/"},{"key":"e_1_3_3_55_2","unstructured":"NVIDIA. 2018. NVIDIA\u2019s Xavier System-on-Chip HotChips 30. Retrieved August 27 2024 from https:\/\/fuse.wikichip.org\/news\/1618\/hot-chips-30-nvidia-xavier-soc\/"},{"key":"e_1_3_3_56_2","article-title":"HashCC: Lightweight method to improve the quality of the camera-less NeRF scene generation","author":"Olszewski Jan","year":"2023","unstructured":"Jan Olszewski. 2023. HashCC: Lightweight method to improve the quality of the camera-less NeRF scene generation. arXiv preprint arXiv:2305.04296 (2023).","journal-title":"arXiv preprint arXiv:2305.04296"},{"key":"e_1_3_3_57_2","first-page":"87","volume-title":"Proceedings of the Conference on High Performance Graphics","author":"Pantaleoni Jacopo","year":"2010","unstructured":"Jacopo Pantaleoni and David Luebke. 2010. HLBVH: Hierarchical LBVH construction for real-time ray tracing of dynamic geometry. In Proceedings of the Conference on High Performance Graphics. 87\u201395."},{"key":"e_1_3_3_58_2","volume-title":"Physically Based Rendering: From Theory to Implementation","author":"Pharr Matt","year":"2023","unstructured":"Matt Pharr, Wenzel Jakob, and Greg Humphreys. 2023. Physically Based Rendering: From Theory to Implementation. MIT Press."},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258791"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080256"},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555505"},{"key":"e_1_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401196"},{"key":"e_1_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.5555\/1628957"},{"key":"e_1_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3105762.3105771"},{"key":"e_1_3_3_66_2","volume-title":"Image-Based Rendering","author":"Shum Heung-Yeung","year":"2008","unstructured":"Heung-Yeung Shum, Shing-Chow Chan, and Sing Bing Kang. 2008. Image-Based Rendering. Springer Science & Business Media."},{"key":"e_1_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00063"},{"key":"e_1_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.vlsi.2017.02.002"},{"key":"e_1_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34372-9_14"},{"key":"e_1_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.00494"},{"key":"e_1_3_3_72_2","first-page":"211","article-title":"Sparse Bayesian learning and the relevance vector machine","author":"Tipping Michael E.","year":"2001","unstructured":"Michael E. Tipping. 2001. Sparse Bayesian learning and the relevance vector machine. Journal of Machine Learning Research 1 (June 2001), 211\u2013244.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"e_1_3_3_75_2","article-title":"Recent advances in 3D Gaussian splatting","author":"Wu Tong","year":"2024","unstructured":"Tong Wu, Yu-Jie Yuan, Ling-Xiao Zhang, Jie Yang, Yan-Pei Cao, Ling-Qi Yan, and Lin Gao. 2024. Recent advances in 3D Gaussian splatting. arXiv preprint arXiv:2403.11134 (2024).","journal-title":"arXiv preprint arXiv:2403.11134"},{"key":"e_1_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"e_1_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623792"},{"key":"e_1_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071018"},{"key":"e_1_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC53511.2021.00029"},{"key":"e_1_3_3_80_2","article-title":"Euphrates: Algorithm-SoC co-design for low-power mobile continuous vision","author":"Zhu Yuhao","year":"2018","unstructured":"Yuhao Zhu, Anand Samajdar, Matthew Mattina, and Paul Whatmough. 2018. Euphrates: Algorithm-SoC co-design for low-power mobile continuous vision. arXiv preprint arXiv:1803.11232 (2018).","journal-title":"arXiv preprint arXiv:1803.11232"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689340","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:45Z","timestamp":1750291545000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":79,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,12,31]]}},"alternative-id":["10.1145\/3689340"],"URL":"https:\/\/doi.org\/10.1145\/3689340","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"value":"1544-3566","type":"print"},{"value":"1544-3973","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"2024-05-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}