{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:12:58Z","timestamp":1775779978006,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031919886","type":"print"},{"value":"9783031919893","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-91989-3_2","type":"book-chapter","created":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T17:32:59Z","timestamp":1748194379000},"page":"14-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["On Scaling Up 3D Gaussian Splatting Training"],"prefix":"10.1007","author":[{"given":"Hexu","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Haoyang","family":"Weng","sequence":"additional","affiliation":[]},{"given":"Daohan","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Ang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jinyang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Aurojit","family":"Panda","sequence":"additional","affiliation":[]},{"given":"Saining","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","unstructured":"Barron, J., Mildenhall, B., Verbin, D., Srinivasan, P., Hedman, P.: Mip-nerf 360: unbounded anti-aliased neural radiance fields. In: CVPR (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00539","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"2_CR2","unstructured":"Busbridge, D., et al.: How to scale your EMA. In: NeurIPS (2023). https:\/\/openreview.net\/forum?id=DkeeXVdQyu"},{"key":"2_CR3","unstructured":"Ginsburg, B., Gitman, I., You, Y.: Large batch training of convolutional networks with layer-wise adaptive rate scaling (2018). https:\/\/openreview.net\/forum?id=rJ4uaX2aW"},{"key":"2_CR4","unstructured":"Goyal, P., et al.: Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"issue":"173","key":"2_CR5","first-page":"1","volume":"23","author":"D Granziol","year":"2022","unstructured":"Granziol, D., Zohren, S., Roberts, S.: Learning rates as a function of batch size: a random matrix theory approach to neural network training. J. Mach. Learn. Res. 23(173), 1\u201365 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Hedman, P., Philip, J., Price, T., Frahm, J.M., Drettakis, G., Brostow, G.: Deep blending for free-viewpoint image-based rendering. ACM Trans. Graph. (Proc. SIGGRAPH Asia) (2018)","DOI":"10.1145\/3272127.3275084"},{"key":"2_CR7","unstructured":"Huang, Y., et al.: Gpipe: efficient training of giant neural networks using pipeline parallelism. In: NeurIPS (2019). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/093f65e080a295f8076b1c5722a46aa2-Paper.pdf"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Meuleman, A., Kopanas, G., Wimmer, M., Lanvin, A., Drettakis, G.: A hierarchical 3d gaussian representation for real-time rendering of very large datasets. ACM Trans. Graph. (2024). https:\/\/repo-sam.inria.fr\/fungraph\/hierarchical-3d-gaussians\/","DOI":"10.1145\/3658160"},{"key":"2_CR10","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: generalization gap and sharp minima. In: ICLR (2017). https:\/\/openreview.net\/forum?id=H1oyRlYgg"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Knapitsch, A., Park, J., Zhou, Q.Y., Koltun, V.: Tanks and temples: benchmarking large-scale scene reconstruction. ACM Trans. Graph. (2017)","DOI":"10.1145\/3072959.3073599"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Li, R., Fidler, S., Kanazawa, A., Williams, F.: Nerf-xl: scaling nerfs with multiple gpus (2024)","DOI":"10.1007\/978-3-031-73195-2_6"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Pytorch distributed: experiences on accelerating data parallel training. In: VLDB (2020)","DOI":"10.14778\/3415478.3415530"},{"key":"2_CR14","unstructured":"Li, S., et\u00a0al.: Surge phenomenon in optimal learning rate and batch size scaling. arXiv preprint arXiv:2405.14578 (2024)"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Matrixcity: a large-scale city dataset for city-scale neural rendering and beyond. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"2_CR16","unstructured":"Li, Z., Malladi, S., Arora, S.: On the validity of modeling SGD with stochastic differential equations (SDEs). In: NeurIPS (2021). https:\/\/openreview.net\/forum?id=goEdyJ_nVQI"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: Vastgaussian: vast 3d gaussians for large scene reconstruction. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00494"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Guan, H., Luo, C., Fan, L., Peng, J., Zhang, Z.: Citygaussian: real-time high-quality large-scale scene rendering with gaussians. In: CVPR (2024)","DOI":"10.1007\/978-3-031-72640-8_15"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Lu, T., et al.: Scaffold-gs: structured 3d gaussians for view-adaptive rendering. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"2_CR20","unstructured":"Malladi, S., Lyu, K., Panigrahi, A., Arora, S.: On the SDEs and scaling rules for adaptive gradient algorithms. In: NeurIPS (2022). https:\/\/openreview.net\/forum?id=F2mhzjHkQP"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et al.: Pipedream: generalized pipeline parallelism for dnn training. In: SOSP (2019)","DOI":"10.1145\/3341301.3359646"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et al.: Efficient large-scale language model training on gpu clusters using megatron-lm. In: SOSP (2021)","DOI":"10.1145\/3458817.3476209"},{"key":"2_CR24","unstructured":"NERSC: Perlmutter architecture. https:\/\/docs.nersc.gov\/systems\/perlmutter\/architecture\/, Accessed 22 May 2024"},{"key":"2_CR25","unstructured":"Qiao, A., et al.: Pollux: co-adaptive cluster scheduling for goodput-optimized deep learning. In: OSDI (2021)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: SC (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Ren, K., et al.: Octree-gs: towards consistent real-time rendering with lod-structured 3d gaussians. arXiv preprint arXiv:2403.17898 (2024)","DOI":"10.1109\/TPAMI.2025.3568201"},{"key":"2_CR28","unstructured":"Shoeybi, M., Patwary, M., Puri, R., LeGresley, P., Casper, J., Catanzaro, B.: Megatron-lm: training multi-billion parameter language models using model parallelism. In: SC (2020)"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Turki, H., Ramanan, D., Satyanarayanan, M.: Mega-nerf: scalable construction of large-scale nerfs for virtual fly-throughs. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01258"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Wang, M., Huang, C.c., Li, J.: Supporting very large models using automatic dataflow graph partitioning. In: EuroSys (2019)","DOI":"10.1145\/3302424.3303953"},{"key":"2_CR31","unstructured":"Xu, Y., et al.: Gspmd: general and scalable parallelization for ml computation graphs. In: arXiv:2105.04663 (2021)"},{"key":"2_CR32","unstructured":"You, Y., et al.: Large batch optimization for deep learning: training bert in 76 minutes. In: ICLR (2020). https:\/\/openreview.net\/forum?id=Syx4wnEtvH"},{"key":"2_CR33","unstructured":"Yuanbo, X., et al.: Bungeenerf: progressive neural radiance field for extreme multi-scale scene rendering. In: ECCV (2022)"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Pytorch fsdp: experiences on scaling fully sharded data parallel (2023)","DOI":"10.14778\/3611540.3611569"},{"key":"2_CR35","unstructured":"Zheng, L., et\u00a0al.: Alpa: automating inter-and intra-operator parallelism for distributed deep learning. In: OSDI (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91989-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T17:33:09Z","timestamp":1748194389000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91989-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031919886","9783031919893"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91989-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}