{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:48:34Z","timestamp":1782748114144,"version":"3.54.5"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Science Foundation","award":["2221812"],"award-info":[{"award-number":["2221812"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Comput. Graph. Interact. Tech."],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:p>\n                    The application of machine learning techniques to 3D Gaussian Splatting (3DGS) has enabled high-fidelity interactive rendering of complex 3D scenes on modest compute resources, offering significant potential for scientific visualization. However, the memory demands of reconstructing large-scale scientific volumes at high fidelity exceed the capacity of individual GPUs. While distributed 3DGS frameworks exist for urban scenes, they rely on global scene analysis or frequent all-to-all communication, inherently limiting their scalability on High-Performance Computing (HPC) clusters. In this paper, we present a scalable distributed 3DGS training and rendering framework designed for large-scale scientific volumetric data. Leveraging the native domain decomposition of HPC simulations, our approach treats each spatial partition as an independent optimization task that avoids device-to-device communication. We further exploit temporal coherence in simulation data to accelerate training on subsequent timesteps. We perform experimental studies demonstrating that our approach achieves near-ideal weak scaling by eliminating synchronization overhead. Additionally, we evaluate the trade-offs of the standard 3DGS optimization strategy against a Markov Chain Monte Carlo (MCMC) approach. We find that while standard 3DGS produces higher quality reconstructions with larger Gaussian footprints, MCMC effectively bounds the primitive count at scale in exchange for a minor reduction in fidelity. Furthermore, we demonstrate that our temporal fine-tuning strategy for time-series data remains robust at scale, establishing a reliable path towards\n                    <jats:italic toggle=\"yes\">in situ<\/jats:italic>\n                    applications of 3DGS for massive scientific simulations.\n                  <\/jats:p>","DOI":"10.1145\/3820022","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:37:39Z","timestamp":1782747459000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Training and Rendering of 3D Gaussians for Large Scale Scientific Data 55"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3262-8588","authenticated-orcid":false,"given":"Andres","family":"Sewell","sequence":"first","affiliation":[{"name":"Computer Science","place":["Logan, USA"]},{"name":"Utah State University","place":["Logan, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7165-273X","authenticated-orcid":false,"given":"Mengjiao","family":"Han","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory","place":["Lemont, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0342-9366","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"NVIDIA","place":["Santa Clara, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2649-1595","authenticated-orcid":false,"given":"Steve","family":"Petruzza","sequence":"additional","affiliation":[{"name":"Computer Science","place":["Logan, USA"]},{"name":"Utah State University","place":["Logan, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"e_1_3_2_2_1","volume-title":"Second Eurographics Workshop on Parallel Graphics and Visualization, 1998","author":"Ahrens James","year":"1998","unstructured":"James Ahrens. 1998. Efficient sort-last rendering using compression-based image compositing. In Second Eurographics Workshop on Parallel Graphics and Visualization, 1998."},{"key":"e_1_3_2_3_1","unstructured":"Kuangshi Ai Kaiyuan Tang and Chaoli Wang. 2025. NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.12621 (2025)."},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2005.1532785"},{"key":"e_1_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Yu Chen and Gim\u00a0Hee Lee. 2024. Dogs: Distributed-oriented gaussian splatting for large-scale 3d reconstruction via gaussian consensus. Advances in Neural Information Processing Systems 37 (2024) 34487\u201334512.","DOI":"10.52202\/079017-1087"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","unstructured":"Ronald\u00a0H. Cohen William\u00a0P. Dannevik Andris\u00a0M. Dimits Donald\u00a0E. Eliason Arthur\u00a0A. Mirin Ye Zhou David\u00a0H. Porter and Paul\u00a0R. Woodward. 2002. Three-dimensional simulation of a Richtmyer\u2013Meshkov instability with a two-scale initial perturbation. Physics of Fluids 14 10 (oct 2002) 3692\u20133709. doi:10.1063\/1.1504452","DOI":"10.1063\/1.1504452"},{"key":"e_1_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Landon Dyken Andres Sewell Will Usher Nathan Debardeleben Steve Petruzza and Sidharth Kumar. 2025. Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.13339 (2025).","DOI":"10.1109\/TVCG.2026.3694460"},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","unstructured":"Stefan Eilemann and Renato Pajarola. 2007. Direct Send Compositing for Parallel Sort-Last Rendering. ACM SIGGRAPH ASIA 2008 Courses SIGGRAPH Asia\u201908 29\u201336. doi:10.2312\/EGPGV\/EGPGV07\/029-036","DOI":"10.2312\/EGPGV\/EGPGV07\/029-036"},{"key":"e_1_3_2_9_1","unstructured":"Ashley Gosselin-Ildari. 2005. Lampropeltis getula (Common Kingsnake). Digital Morphology. http:\/\/digimorph.org\/specimens\/Lampropeltis_getula\/egg\/whole\/ Accessed: 2026-02-06. Scanned by the University of Texas High-Resolution X-ray CT Facility (UTCT). Funding provided by NSF grant IIS-9874781."},{"key":"e_1_3_2_10_1","unstructured":"Mengjiao Han Andres Sewell Joseph Insley Janet Knowles Victor\u00a0A. Mateevitsi Michael\u00a0E. Papka Steve Petruzza and Silvio Rizzi. 2025. Distributed 3D Gaussian Splatting for High-Resolution Isosurface Visualization. arxiv:https:\/\/arXiv.org\/abs\/2509.12138\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2509.12138"},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","unstructured":"Junkai Huang Saswat Subhajyoti\u00a0Mallick Alejandro Amat Marc Ruiz\u00a0Olle Albert Mosella-Montoro Bernhard Kerbl Francisco Vicente\u00a0Carrasco and Fernando De\u00a0la Torre. 2025. Echoes of the Coliseum: Towards 3D Live streaming of Sports Events. ACM Trans. Graph. 44 4 Article 46 (July 2025) 17\u00a0pages. doi:10.1145\/3731214","DOI":"10.1145\/3731214"},{"key":"e_1_3_2_12_1","unstructured":"Saqib Javed Ahmad\u00a0Jarrar Khan Corentin Dumery Chen Zhao and Mathieu Salzmann. 2024. Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes. ArXiv abs\/2412.05700 (2024). https:\/\/api.semanticscholar.org\/CorpusID:274597860"},{"key":"e_1_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Andreas Meuleman Georgios Kopanas Michael Wimmer Alexandre Lanvin and George Drettakis. 2024. A hierarchical 3d gaussian representation for real-time rendering of very large datasets. ACM Transactions on Graphics (TOG) 43 4 (2024) 1\u201315.","DOI":"10.1145\/3658160"},{"key":"e_1_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Shakiba Kheradmand Daniel Rebain Gopal Sharma Weiwei Sun Yang-Che Tseng Hossam Isack Abhishek Kar Andrea Tagliasacchi and Kwang\u00a0Moo Yi. 2024. 3d gaussian splatting as markov chain monte carlo. Advances in Neural Information Processing Systems 37 (2024) 80965\u201380986.","DOI":"10.52202\/079017-2573"},{"key":"e_1_3_2_16_1","doi-asserted-by":"crossref","unstructured":"Yong Kou Yanci Zhang Zenghui Fan Xia Yuan Haobo Liang Dening Luo and Qing Ye. 2026. AccelGS: An Acceleration Framework for Large-Scale 3D Gaussian Splatting Training. ICASSP 2026 - 2026 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) (2026). https:\/\/api.semanticscholar.org\/CorpusID:287693622","DOI":"10.1109\/ICASSP55912.2026.11465147"},{"key":"e_1_3_2_17_1","unstructured":"Jonas Kulhanek Marie-Julie Rakotosaona Fabian Manhardt Christina Tsalicoglou Michael Niemeyer Torsten Sattler Songyou Peng and Federico Tombari. 2025. LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.23158 (2025)."},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/LDAV.2016.7874308"},{"key":"e_1_3_2_19_1","unstructured":"Bingling Li Shengyi Chen Luchao Wang Kaimin Liao Sijie Yan and Yuanjun Xiong. 2024. Retinags: Scalable training for dense scene rendering with billion-scale 3d gaussians. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.11836 (2024)."},{"key":"e_1_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Yi Li Eric Perlman Minping Wan Yunke Yang Charles Meneveau R Burns Shiyi Chen A Shraiman and Alexander\u00a0S Szalay. 2008. A public turbulence database cluster and applications to study Lagrangian evolution of velocity increments in turbulence. Journal of Turbulence9 (2008) N31.","DOI":"10.1080\/14685240802376389"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00494"},{"key":"e_1_3_2_22_1","first-page":"265","volume-title":"European Conference on Computer Vision","author":"Liu Yang","year":"2024","unstructured":"Yang Liu, Chuanchen Luo, Lue Fan, Naiyan Wang, Junran Peng, and Zhaoxiang Zhang. 2024. Citygaussian: Real-time high-quality large-scale scene rendering with gaussians. In European Conference on Computer Vision. Springer, 265\u2013282."},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"e_1_3_2_25_1","unstructured":"Jessie Maisano. 2003. Chamaeleo calyptratus (On-line). Digital Morphology. http:\/\/digimorph.org\/specimens\/Chamaeleo_calyptratus\/whole\/ Accessed: 2026-02-06."},{"key":"e_1_3_2_26_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_27_1","doi-asserted-by":"crossref","unstructured":"Nicolas Moenne-Loccoz Ashkan Mirzaei Or Perel Riccardo de Lutio Janick\u00a0Martinez Esturo Gavriel State Sanja Fidler Nicholas Sharp and Zan Gojcic. 2024. 3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes. ACM Transactions on Graphics and SIGGRAPH Asia (2024).","DOI":"10.1145\/3687934"},{"key":"e_1_3_2_28_1","doi-asserted-by":"crossref","unstructured":"Steven Molnar Michael Cox David Ellsworth and Henry Fuchs. 2002. A sorting classification of parallel rendering. IEEE computer graphics and applications 14 4 (2002) 23\u201332.","DOI":"10.1109\/38.291528"},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/502125.502141"},{"key":"e_1_3_2_30_1","volume-title":"IceT users\u2019 guide and reference.","author":"Moreland Kenneth\u00a0D","year":"2010","unstructured":"Kenneth\u00a0D Moreland. 2010. IceT users\u2019 guide and reference. Technical Report. Sandia National Laboratories."},{"key":"e_1_3_2_31_1","volume-title":"IceT (Chapter in High Performance Visualization).","author":"Moreland Kenneth\u00a0D","year":"2011","unstructured":"Kenneth\u00a0D Moreland. 2011. IceT (Chapter in High Performance Visualization). Technical Report. Sandia National Lab.(SNL-NM), Albuquerque, NM (United States)."},{"key":"e_1_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/1038266.1039015"},{"key":"e_1_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/LDAV64567.2024.00009"},{"key":"e_1_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Kerui Ren Lihan Jiang Tao Lu Mulin Yu Linning Xu Zhangkai Ni and Bo Dai. 2024. Octree-gs: Towards consistent real-time rendering with lod-structured 3d gaussians. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.17898 (2024).","DOI":"10.1109\/TPAMI.2025.3568201"},{"key":"e_1_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"e_1_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/LDAV64567.2024.00018"},{"key":"e_1_3_2_38_1","unstructured":"Siemens Medical Solutions. 2026. CT Head (Skull). The Volume Library. https:\/\/klacansky.com\/open-scivis-datasets\/ Accessed: 2026-02-06. Original source: Siemens Medical Solutions Forchheim Germany."},{"key":"e_1_3_2_39_1","doi-asserted-by":"crossref","unstructured":"Kaiyuan Tang Siyuan Yao and Chaoli Wang. 2025. iVR-GS: Inverse Volume Rendering for Explorable Visualization via Editable 3D Gaussian Splatting. IEEE Transactions on Visualization and Computer Graphics (2025).","DOI":"10.1109\/TVCG.2025.3567121"},{"key":"e_1_3_2_40_1","doi-asserted-by":"publisher","unstructured":"Qi Wu Joseph\u00a0A. Insley Victor\u00a0A. Mateevitsi Silvio Rizzi Michael\u00a0E. Papka and Kwan-Liu Ma. 2025a. Distributed Neural Representation for Reactive In Situ Visualization. IEEE Transactions on Visualization and Computer Graphics 31 9 (2025) 5199\u20135214. doi:10.1109\/TVCG.2024.3432710","DOI":"10.1109\/TVCG.2024.3432710"},{"key":"e_1_3_2_41_1","doi-asserted-by":"crossref","unstructured":"Qi Wu Janick Martinez\u00a0Esturo Ashkan Mirzaei Nicolas Moenne-Loccoz and Zan Gojcic. 2025b. 3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting. Conference on Computer Vision and Pattern Recognition (CVPR) (2025).","DOI":"10.1109\/CVPR52734.2025.02425"},{"key":"e_1_3_2_42_1","doi-asserted-by":"crossref","unstructured":"Brian Wylie Constantine Pavlakos Vasily Lewis and Ken Moreland. 2001. Scalable rendering on PC clusters. IEEE Computer Graphics and Applications 21 4 (2001) 62\u201369.","DOI":"10.1109\/38.933525"},{"key":"e_1_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00420"},{"key":"e_1_3_2_44_1","unstructured":"Siyuan Yao and Chaoli Wang. 2025. VolSegGS: Segmentation and Tracking in Dynamic Volumetric Scenes via Deformable 3D Gaussians. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.12667 (2025)."},{"key":"e_1_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413419"},{"key":"e_1_3_2_46_1","first-page":"14","volume-title":"European Conference on Computer Vision","author":"Zhao Hexu","year":"2024","unstructured":"Hexu Zhao, Haoyang Weng, Daohan Lu, Ang Li, Jinyang Li, Aurojit Panda, and Saining Xie. 2024. On scaling up 3d gaussian splatting training. In European Conference on Computer Vision. Springer, 14\u201336."}],"container-title":["Proceedings of the ACM on Computer Graphics and Interactive Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3820022","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3820022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:43:01Z","timestamp":1782747781000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3820022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,1]]}},"alternative-id":["10.1145\/3820022"],"URL":"https:\/\/doi.org\/10.1145\/3820022","relation":{},"ISSN":["2577-6193"],"issn-type":[{"value":"2577-6193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"assertion":[{"value":"2026-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}