{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T11:23:04Z","timestamp":1784546584359,"version":"3.55.0"},"reference-count":72,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T00:00:00Z","timestamp":1709078400000},"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":[[2024,4,30]]},"abstract":"<jats:p>We introduce NeuralVDB, which improves on an existing industry standard for efficient storage of sparse volumetric data, denoted VDB\u00a0[Museth<jats:xref ref-type=\"bibr\">2013<\/jats:xref>], by leveraging recent advancements in machine learning. Our novel hybrid data structure can reduce the memory footprints of VDB volumes by orders of magnitude, while maintaining its flexibility and only incurring small (user-controlled) compression errors. Specifically, NeuralVDB replaces the lower nodes of a shallow and wide VDB tree structure with multiple hierarchical neural networks that separately encode topology and value information by means of neural classifiers and regressors respectively. This approach is proven to maximize the compression ratio while maintaining the spatial adaptivity offered by the higher-level VDB data structure. For sparse signed distance fields and density volumes, we have observed compression ratios on the order of 10\u00d7 to more than 100\u00d7 from already compressed VDB inputs, with little to no visual artifacts. Furthermore, NeuralVDB is shown to offer more effective compression performance compared to other neural representations such as Neural Geometric Level of Detail\u00a0[Takikawa et\u00a0al.<jats:xref ref-type=\"bibr\">2021<\/jats:xref>], Variable Bitrate Neural Fields\u00a0[Takikawa et\u00a0al.<jats:xref ref-type=\"bibr\">2022a<\/jats:xref>], and Instant Neural Graphics Primitives\u00a0[M\u00fcller et\u00a0al.<jats:xref ref-type=\"bibr\">2022<\/jats:xref>]. Finally, we demonstrate how warm-starting from previous frames can accelerate training, i.e.,\u00a0compression, of animated volumes as well as improve temporal coherency of model inference, i.e.,\u00a0decompression.<\/jats:p>","DOI":"10.1145\/3641817","type":"journal-article","created":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T12:29:18Z","timestamp":1706012958000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8932-5519","authenticated-orcid":false,"given":"Doyub","family":"Kim","sequence":"first","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6387-1081","authenticated-orcid":false,"given":"Minjae","family":"Lee","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"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, Santa Clara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,2,28]]},"reference":[{"key":"e_1_3_3_2_1","first-page":"491","article-title":"Patient MoCap: Human pose estimation under blanket occlusion for hospital monitoring applications","author":"Achilles Felix","year":"2016","unstructured":"Felix Achilles, Alexandru-Eugen Ichim, Huseyin Coskun, Federico Tombari, Soheyl Noachtar, and Nassir Navab. 2016. Patient MoCap: Human pose estimation under blanket occlusion for hospital monitoring applications. Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2016: 19th International Conference, 491\u2013499.","journal-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2016: 19th International Conference"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1122501.1122503"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-73333-4"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988458.2988490"},{"key":"e_1_3_3_6_1","unstructured":"A. Brock Th. Lim J. M. Ritchie and N. Weston. 2016. Generative and discriminative voxel modeling with convolutional neural networks. CoRR abs\/1608.04236 (2016)."},{"key":"e_1_3_3_7_1","article-title":"Learning implicit fields for generative shape modeling","author":"Chen Zhiqin","year":"2019","unstructured":"Zhiqin Chen and Hao Zhang. 2019. Learning implicit fields for generative shape modeling. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019).","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_3_8_1","doi-asserted-by":"crossref","unstructured":"Nuttapong Chentanez and Matthias M\u00fcller. 2011. Real-time Eulerian water simulation using a restricted tall cell grid. ACM Transactions on Graphics 30 4 (2011) 1\u201310.","DOI":"10.1145\/2010324.1964977"},{"key":"e_1_3_3_9_1","unstructured":"Thomas Davies Derek Nowrouzezahrai and Alec Jacobson. 2020. On the effectiveness of weight-encoded neural implicit 3D shapes. arXiv:2009.09808. Retrieved from https:\/\/arxiv.org\/abs\/2009.09808"},{"key":"e_1_3_3_10_1","unstructured":"Jean-loup Gailly and Mark Adler. 2004. Zlib compression library. (2004)."},{"key":"e_1_3_3_11_1","doi-asserted-by":"crossref","unstructured":"P. Hedman P. P. Srinivasan B. Mildenhall J. T. Barron and P. Debevec. 2021. Baking neural radiance fields for real-time view synthesis. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV\u201921). 5855\u20135864.","DOI":"10.1109\/ICCV48922.2021.00582"},{"key":"e_1_3_3_12_1","first-page":"109","volume-title":"Proceedings of the High Performance Graphics","author":"Hoetzlein Rama Karl","year":"2016","unstructured":"Rama Karl Hoetzlein. 2016. GVDB: Raytracing sparse voxel database structures on the GPU. In Proceedings of the High Performance Graphics. 109\u2013117."},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1122501.1122508"},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141959"},{"key":"e_1_3_3_15_1","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume":"31","author":"Jacot Arthur","year":"2018","unstructured":"Arthur Jacot, Franck Gabriel, and Clement Hongler. 2018. Neural tangent kernel: Convergence and generalization in neural networks. Advances in Neural Information Processing Systems 31 (2018).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_16_1","volume-title":"EmberGen VDB Dataset","year":"2020","unstructured":"JangaFX. 2020. EmberGen VDB Dataset. Accessed: 2022-02-15."},{"key":"e_1_3_3_17_1","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980"},{"issue":"5","key":"e_1_3_3_18_1","first-page":"3203","article-title":"Overview of the neural network compression and representation (NNR) standard","volume":"32","year":"2021","unstructured":"Heiner Kirchhoffer, Paul Haase, Wojciech Samek, Karsten M\u00fcller, Hamed Rezazadegan-Tavakoli, Francesco Cricri, Emre B. Aksu, Miska M. Hannuksela, Wei Jiang, Wei Wang, Shan Liu, Swayambhoo Jain, Shahab Hamidi-Rad, Fabien Racap\u00e9, and Werner Bailer. 2021. Overview of the neural network compression and representation (NNR) standard. IEEE Transactions on Circuits and Systems for Video Technology 32, 5 (2021), 3203\u20133216.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196909"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103090"},{"key":"e_1_3_3_21_1","article-title":"A skinned tetrahedral mesh for hair animation and hair-water interaction","author":"Lee Minjae","year":"2018","unstructured":"Minjae Lee, David Hyde, Michael Bao, and Ronald Fedkiw. 2018. A skinned tetrahedral mesh for hair animation and hair-water interaction. IEEE Transactions on Visualization and Computer Graphics (2018).","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_3_22_1","doi-asserted-by":"crossref","unstructured":"Minjae Lee David Hyde Kevin Li and Ronald Fedkiw. 2019. A robust volume conserving method for character-water interaction. In Proceedings of the 18th annual ACM SIGGRAPH\/Eurographics Symposium on Computer Animation. 1\u201312.","DOI":"10.1145\/3309486.3340244"},{"key":"e_1_3_3_23_1","doi-asserted-by":"crossref","unstructured":"Randall J. Leveque. 1996. High-resolution conservative algorithms for advection in incompressible flow. SIAM Journal on Numerical Analysis 33 2 (1996) 627\u2013665.","DOI":"10.1137\/0733033"},{"key":"e_1_3_3_24_1","unstructured":"Yuanzhan Li Yuqi Liu Yujie Lu Siyu Zhang Shen Cai and Yanting Zhang. 2022. High-fidelity 3D model compression based on key spheres. arXiv:2201.07486. Retrieved from https:\/\/arxiv.org\/abs\/2201.07486"},{"key":"e_1_3_3_25_1","unstructured":"Lingjie Liu Jiatao Gu Kyaw Zaw Lin Tat-Seng Chua and Christian Theobalt. 2020. Neural sparse voxel fields. Advances in Neural Information Processing Systems 33 (2020) 15651\u201315663."},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196022"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015745"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910119"},{"key":"e_1_3_3_29_1","volume-title":"CT Scan of a Chameleon","author":"Maisano Jessie","year":"2003","unstructured":"Jessie Maisano. 2003. CT Scan of a Chameleon. Accessed: 2022-02-15."},{"key":"e_1_3_3_30_1","unstructured":"Julien N. P. Martel David B. Lindell Connor Z. Lin Eric R. Chan Marco Monteiro and Gordon Wetzstein. 2021. ACORN: Adaptive coordinate networks for neural scene representation. arXiv:2105.02788. Retrieved from https:\/\/arxiv.org\/abs\/2105.02788"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00484"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_35_1","unstructured":"Ben Moseley Andrew Markham and Tarje Nissen-Meyer. 2021. Finite basis physics-informed neural networks (FBPINNs): A scalable domain decomposition approach for solving differential equations. arXiv:2107.07871. Retrieved from https:\/\/arxiv.org\/abs\/2107.07871"},{"key":"e_1_3_3_36_1","doi-asserted-by":"crossref","unstructured":"Thomas M\u00fcller Alex Evans Christoph Schied and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. arXiv:2201.05989. Retrieved from https:\/\/arxiv.org\/abs\/2201.05989","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341156"},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417804"},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459812"},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2037826.2037894"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487228.2487235"},{"key":"e_1_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450623.3464653"},{"key":"e_1_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-005-9062-8"},{"key":"e_1_3_3_44_1","article-title":"Compressed progressive meshes","author":"Pajarola Renato","year":"2000","unstructured":"Renato Pajarola and J. Rossignac. 2000. Compressed progressive meshes. IEEE Transactions on Visualization and Computer Graphics (2000).","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_3_3_46_1","first-page":"8024","volume-title":"Proceedings of the Advances in Neural Information Processing Systems.","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary 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. In Proceedings of the Advances in Neural Information Processing Systems.H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Curran Associates, Inc., 8024\u20138035. Retrieved from http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.1999.6345"},{"key":"e_1_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_31"},{"key":"e_1_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/573326"},{"key":"e_1_3_3_50_1","first-page":"5301","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Rahaman Nasim","year":"2019","unstructured":"Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred Hamprecht, Yoshua Bengio, and Aaron Courville. 2019. On the spectral bias of neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 5301\u20135310."},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275019"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073368.1073398"},{"key":"e_1_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661269"},{"key":"e_1_3_3_54_1","volume-title":"Proceedings of the ICLR (Poster)","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc V. Le, Geoffrey E. Hinton, and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. In Proceedings of the ICLR (Poster)."},{"key":"e_1_3_3_55_1","unstructured":"Vincent Sitzmann Eric Chan Richard Tucker Noah Snavely and Gordon Wetzstein. 2020. Metasdf: Meta-learning signed distance functions. Advances in Neural Information Processing Systems 33 (2020) 10136\u201310147."},{"key":"e_1_3_3_56_1","unstructured":"Vincent Sitzmann Julien Martel Alexander Bergman David Lindell and Gordon Wetzstein. 2020. Implicit neural representations with periodic activation functions. Advances in Neural Information Processing Systems 33 (2020) 7462\u20137473."},{"key":"e_1_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.2001.6740"},{"key":"e_1_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530727"},{"key":"e_1_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01120"},{"key":"e_1_3_3_60_1","article-title":"Kaolin Wisp: A PyTorch Library and Engine for Neural Fields Research","author":"Takikawa Towaki","year":"2022","unstructured":"Towaki Takikawa, Or Perel, Clement Fuji Tsang, Charles Loop, Joey Litalien, Jonathan Tremblay, Sanja Fidler, and Maria Shugrina. 2022b. Kaolin Wisp: A PyTorch Library and Engine for Neural Fields Research. Retrieved April 4th, 2023 from https:\/\/github.com\/NVIDIAGameWorks\/kaolin-wisp","journal-title":"R"},{"key":"e_1_3_3_61_1","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","author":"Tancik Matthew","year":"2020","unstructured":"Matthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, and Ren Ng. 2020. Fourier features let networks learn high frequency functions in low dimensional domains. NeurIPS (2020).","journal-title":"NeurIPS"},{"issue":"6","key":"e_1_3_3_62_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3272127.3275096","article-title":"Real-time compression and streaming of 4d performances","volume":"37","author":"Tang Danhang","year":"2018","unstructured":"Danhang Tang, Mingsong Dou, Peter Lincoln, Philip Davidson, Kaiwen Guo, Jonathan Taylor, Sean Fanello, Cem Keskin, Adarsh Kowdle, Sofien Bouaziz, et\u00a0al. 2018. Real-time compression and streaming of 4d performances. ACM Transactions on Graphics 37, 6 (2018), 1\u201311.","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00137"},{"key":"e_1_3_3_64_1","volume-title":"Blosc","author":"Team The Blosc Development","year":"2020","unstructured":"The Blosc Development Team. 2020. Blosc. Accessed: 2022-02-04."},{"key":"e_1_3_3_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2004.1260764"},{"key":"e_1_3_3_66_1","article-title":"The book of shaders: Fractal brownian motion","author":"Vivo Patricio Gonzalez","year":"2015","unstructured":"Patricio Gonzalez Vivo and Jen Lowe. 2015. The book of shaders: Fractal brownian motion. Patricio Gonzalez Vivo, https:\/\/thebookofshaders.com\/13 (2015).","journal-title":"Patricio Gonzalez Vivo"},{"key":"e_1_3_3_67_1","article-title":"Vdbfusion: Flexible and efficient tsdf integration of range sensor data","author":"Vizzo Ignacio","year":"2022","unstructured":"Ignacio Vizzo, Tiziano Guadagnino, Jens Behley, and Cyrill Stachniss. 2022. Vdbfusion: Flexible and efficient tsdf integration of range sensor data. Sensors 22, 3 (2022), 1296.","journal-title":"Sensors 22, 3 (2022), 1296"},{"key":"e_1_3_3_68_1","volume-title":"Disney Clouds Dataset","author":"Studios Walt Disney Animation","year":"2017","unstructured":"Walt Disney Animation Studios. 2017. Disney Clouds Dataset. Accessed: 2021-12-09."},{"key":"e_1_3_3_69_1","unstructured":"Magnus Wrenninge Chris Allen Sosh Mirsepassi Stephen Marshall Chris Burdorf Henrik Falt Scot Shinderman and Doug Bloom. 2020. Field3D. Retrieved from https:\/\/github.com\/imageworks\/Field3D"},{"key":"e_1_3_3_70_1","unstructured":"Tong Wu Liang Pan Junzhe Zhang Tai Wang Ziwei Liu and Dahua Lin. 2021. Density-aware chamfer distance as a comprehensive metric for point cloud completion. arXiv:2111.12702. Retrieved from https:\/\/arxiv.org\/abs\/2111.12702"},{"key":"e_1_3_3_71_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14505"},{"key":"e_1_3_3_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_3_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.506"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641817","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:06Z","timestamp":1750291386000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,28]]},"references-count":72,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4,30]]}},"alternative-id":["10.1145\/3641817"],"URL":"https:\/\/doi.org\/10.1145\/3641817","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,28]]},"assertion":[{"value":"2022-11-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-09","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}