{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T11:23:03Z","timestamp":1784546583672,"version":"3.55.0"},"reference-count":41,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T00:00:00Z","timestamp":1721347200000},"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":["ACM Trans. Graph."],"published-print":{"date-parts":[[2024,7,19]]},"abstract":"<jats:p>\n            We present\n            <jats:italic>f<\/jats:italic>\n            VDB, a novel GPU-optimized framework for deep learning on large-scale 3D data.\n            <jats:italic>f<\/jats:italic>\n            VDB provides a complete set of differentiable primitives to build deep learning architectures for common tasks in 3D learning such as convolution, pooling, attention, ray-tracing, meshing, etc.\n            <jats:italic>f<\/jats:italic>\n            VDB simultaneously provides a\n            <jats:italic>much larger<\/jats:italic>\n            feature set (primitives and operators) than established frameworks with no loss in efficiency: our operators match or exceed the performance of other frameworks with narrower scope. Furthermore,\n            <jats:italic>f<\/jats:italic>\n            VDB can process datasets with much larger footprint and spatial resolution than prior works, while providing a competitive memory footprint on small inputs. To achieve this combination of versatility and performance,\n            <jats:italic>f<\/jats:italic>\n            VDB relies on a single novel VDB index grid acceleration structure paired with several key innovations including GPU accelerated sparse grid construction, convolution using tensorcores, fast ray tracing kernels using a Hierarchical Digital Differential Analyzer algorithm (HDDA), and jagged tensors. Our framework is fully integrated with PyTorch enabling interoperability with existing pipelines, and we demonstrate its effectiveness on a number of representative tasks such as large-scale point-cloud segmentation, high resolution 3D generative modeling, unbounded scale Neural Radiance Fields, and large-scale point cloud reconstruction.\n          <\/jats:p>","DOI":"10.1145\/3658226","type":"journal-article","created":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T14:47:57Z","timestamp":1721400477000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["fVDB : A Deep-Learning Framework for Sparse, Large Scale, and High Performance Spatial Intelligence"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2189-881X","authenticated-orcid":false,"given":"Francis","family":"Williams","sequence":"first","affiliation":[{"name":"NVIDIA Research, Brooklyn, NY, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6320-2636","authenticated-orcid":false,"given":"Jiahui","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Santa Clara, CA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1959-6396","authenticated-orcid":false,"given":"Jonathan","family":"Swartz","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Wellington, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4569-5956","authenticated-orcid":false,"given":"Gergely","family":"Klar","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Wellington, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6158-6127","authenticated-orcid":false,"given":"Vijay","family":"Thakkar","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Atlanta, GA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2956-2050","authenticated-orcid":false,"given":"Matthew","family":"Cong","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Santa Clara, CA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6376-7100","authenticated-orcid":false,"given":"Xuanchi","family":"Ren","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7426-7650","authenticated-orcid":false,"given":"Ruilong","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Berkeley, CA, United States of America"},{"name":"University of California Berkeley, Berkeley, CA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0998-1581","authenticated-orcid":false,"given":"Clement","family":"Fuji-Tsang","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1040-3260","authenticated-orcid":false,"given":"Sanja","family":"Fidler","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5608-3085","authenticated-orcid":false,"given":"Eftychios","family":"Sifakis","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI, United States of America"},{"name":"NVIDIA Research, Madison, WI, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9926-780X","authenticated-orcid":false,"given":"Ken","family":"Museth","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Los Angeles, CA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,19]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2023. 3D Karton City model. https:\/\/www.turbosquid.com\/3d-models\/3d-karton-city-2-model-1196110. Accessed: 2023-08-01."},{"key":"e_1_2_1_2_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dandelion Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/Software available from tensorflow.org."},{"key":"e_1_2_1_3_1","unstructured":"Academy Software Foundation (ASWF). 2012 -- 2024. OpenVDB. https:\/\/www.openvdb.org"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211006735"},{"key":"e_1_2_1_6_1","volume-title":"Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang.","author":"Bradbury James","year":"2018","unstructured":"James Bradbury, Roy Frostig, Peter Hawkins, Matthew James Johnson, Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang. 2018. JAX: composable transformations of Python+NumPy programs. http:\/\/github.com\/google\/jax"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363679"},{"key":"e_1_2_1_8_1","unstructured":"Francois Chollet et al. 2015. Keras. https:\/\/github.com\/fchollet\/keras"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"e_1_2_1_10_1","volume-title":"Spconv: Spatially Sparse Convolution Library. https:\/\/github.com\/traveller59\/spconv.","author":"Contributors Spconv","year":"2022","unstructured":"Spconv Contributors. 2022. Spconv: Spatially Sparse Convolution Library. https:\/\/github.com\/traveller59\/spconv."},{"key":"e_1_2_1_11_1","unstructured":"Tri Dao Daniel Y. Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. arXiv:2205.14135 [cs.LG]"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_2_1_13_1","volume-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 3354--3361","author":"Geiger A.","unstructured":"A. Geiger, P. Lenz, and R. Urtasun. 2012. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 3354--3361."},{"key":"e_1_2_1_14_1","volume-title":"DiffTaichi: Differentiable Programming for Physical Simulation. ICLR","author":"Hu Yuanming","year":"2020","unstructured":"Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan Ragan-Kelley, and Fr\u00e9do Durand. 2020. DiffTaichi: Differentiable Programming for Physical Simulation. ICLR (2020)."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356506"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555457"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00425"},{"key":"e_1_2_1_18_1","volume-title":"Artem Rozantsev, Wenzheng Chen, Tommy Xiang, Rev Lebaredian, and Sanja Fidler.","author":"Jatavallabhula Krishna Murthy","year":"2019","unstructured":"Krishna Murthy Jatavallabhula, Edward Smith, Jean-Francois Lafleche, Clement Fuji Tsang, Artem Rozantsev, Wenzheng Chen, Tommy Xiang, Rev Lebaredian, and Sanja Fidler. 2019. Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research. arXiv:1911.05063 [cs.CV]"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_2_1_20_1","volume-title":"NeuralVDB: High-resolution Sparse","author":"Kim Doyub","unstructured":"Doyub Kim, Minjae Lee, and Ken Museth. 2022. NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks. arXiv:2208.04448 [cs.LG]"},{"key":"e_1_2_1_21_1","volume-title":"Nerfacc: Efficient sampling accelerates nerfs. arXiv preprint arXiv:2305.04966","author":"Li Ruilong","year":"2023","unstructured":"Ruilong Li, Hang Gao, Matthew Tancik, and Angjoo Kanazawa. 2023. Nerfacc: Efficient sampling accelerates nerfs. arXiv preprint arXiv:2305.04966 (2023)."},{"key":"e_1_2_1_22_1","unstructured":"Minghua Liu Ruoxi Shi Linghao Chen Zhuoyang Zhang Chao Xu Xinyue Wei Hansheng Chen Chong Zeng Jiayuan Gu and Hao Su. 2023a. One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion. arXiv:2311.07885 [cs.CV]"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1051\/itmconf\/20203203044"},{"key":"e_1_2_1_25_1","volume-title":"NVIDIA Research","author":"Merrill Duane","year":"2015","unstructured":"Duane Merrill. 2015. Cub. NVIDIA Research (2015)."},{"key":"e_1_2_1_26_1","volume-title":"Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG) 41, 4","author":"M\u00fcller Thomas","year":"2022","unstructured":"Thomas M\u00fcller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG) 41, 4 (2022), 1--15."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487228.2487235"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2614106.2614136"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450623.3464653"},{"key":"e_1_2_1_30_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","year":"1912","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv:1912.01703 [cs.LG]"},{"key":"e_1_2_1_31_1","volume-title":"Guibas","author":"Qi Charles R.","year":"2017","unstructured":"Charles R. Qi, Li Yi, Hao Su, and Leonidas J. Guibas. 2017. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. arXiv:1706.02413 [cs.CV]"},{"key":"e_1_2_1_32_1","volume-title":"Accelerating 3D Deep Learning with Py-Torch3D. arXiv:2007.08501","author":"Ravi Nikhila","year":"2020","unstructured":"Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, and Georgia Gkioxari. 2020. Accelerating 3D Deep Learning with Py-Torch3D. arXiv:2007.08501 (2020)."},{"key":"e_1_2_1_33_1","volume-title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies. arXiv preprint","author":"Ren Xuanchi","year":"2023","unstructured":"Xuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth, Sanja Fidler, and Francis Williams. 2023. XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies. arXiv preprint (2023)."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"e_1_2_1_36_1","volume-title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development. In ACM SIGGRAPH 2023 Conference Proceedings (SIGGRAPH '23)","author":"Tancik Matthew","year":"2023","unstructured":"Matthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li, Brent Yi, Justin Kerr, Terrance Wang, Alexander Kristoffersen, Jake Austin, Kamyar Salahi, Abhik Ahuja, David McAllister, and Angjoo Kanazawa. 2023. Nerfstudio: A Modular Framework for Neural Radiance Field Development. In ACM SIGGRAPH 2023 Conference Proceedings (SIGGRAPH '23)."},{"key":"e_1_2_1_37_1","volume-title":"TorchSparse: Efficient Point Cloud Inference Engine. In Conference on Machine Learning and Systems (MLSys)","author":"Tang Haotian","year":"2022","unstructured":"Haotian Tang, Zhijian Liu, Xiuyu Li, Yujun Lin, and Song Han. 2022. TorchSparse: Efficient Point Cloud Inference Engine. In Conference on Machine Learning and Systems (MLSys). Indio, CA, USA."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614303"},{"key":"e_1_2_1_39_1","unstructured":"Vijay Thakkar Pradeep Ramani Cris Cecka Aniket Shivam Honghao Lu Ethan Yan Jack Kosaian Mark Hoemmen Haicheng Wu Andrew Kerr Matt Nicely Duane Merrill Dustyn Blasig Fengqi Qiao Piotr Majcher Paul Springer Markus Hohnerbach Jin Wang and Manish Gupta. 2023. CUTLASS. https:\/\/github.com\/NVIDIA\/cutlass"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073608"},{"key":"e_1_2_1_41_1","volume-title":"Point Transformer. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Zhao Hengshuang","year":"2021","unstructured":"Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip H.S. Torr, and Vladlen Koltun. 2021. Point Transformer. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). New York, NY, USA, 16259--16268."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658226","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:16Z","timestamp":1750291456000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658226"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,19]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7,19]]}},"alternative-id":["10.1145\/3658226"],"URL":"https:\/\/doi.org\/10.1145\/3658226","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,19]]},"assertion":[{"value":"2024-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}