{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T23:40:58Z","timestamp":1783467658751,"version":"3.55.0"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T00:00:00Z","timestamp":1690329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union's Horizon 2020 research and innovation programme","award":["956585"],"award-info":[{"award-number":["956585"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:p>We introduce a practical general-purpose neural appearance filtering pipeline for physically-based rendering. We tackle the previously difficult challenge of aggregating visibility across many levels of detail from local information only, without relying on learning visibility for the entire scene. The high adaptivity of neural representations allows us to retain geometric correlations along rays and thus avoid light leaks. Common approaches to prefiltering decompose the appearance of a scene into volumetric representations with physically-motivated parameters, where the inflexibility of the fitted models limits rendering accuracy. We avoid assumptions on particular types of geometry or materials, bypassing any special-case decompositions. Instead, we directly learn a compressed representation of the intra-voxel light transport. For such high-dimensional functions, neural networks have proven to be useful representations. To satisfy the opposing constraints of prefiltered appearance and correlation-preserving point-to-point visibility, we use two small independent networks on a sparse multi-level voxel grid. Each network requires 10--20 minutes of training to learn the appearance of an asset across levels of detail. Our method achieves 70--95% compression ratios and around 25% of quality improvements over previous work. We reach interactive to real-time framerates, depending on the level of detail.<\/jats:p>","DOI":"10.1145\/3592443","type":"journal-article","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T14:29:21Z","timestamp":1690381761000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Neural Prefiltering for Correlation-Aware Levels of Detail"],"prefix":"10.1145","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4276-1804","authenticated-orcid":false,"given":"Philippe","family":"Weier","sequence":"first","affiliation":[{"name":"DFKI, Saarbr\u00fccken, Germany"},{"name":"Saarland Informatics Campus, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1091-3858","authenticated-orcid":false,"given":"Tobias","family":"Zirr","sequence":"additional","affiliation":[{"name":"Intel Corporation, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8376-6719","authenticated-orcid":false,"given":"Anton","family":"Kaplanyan","sequence":"additional","affiliation":[{"name":"Intel Corporation, Mercer Island, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9379-094X","authenticated-orcid":false,"given":"Ling-Qi","family":"Yan","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2189-2429","authenticated-orcid":false,"given":"Philipp","family":"Slusallek","sequence":"additional","affiliation":[{"name":"DFKI, Saarbr\u00fccken, Germany"},{"name":"Saarland Informatics Campus, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,26]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Fairchild","author":"Andersson Pontus","year":"2020","unstructured":"Pontus Andersson, Jim Nilsson, Tomas Akenine-M\u00f6ller, Magnus Oskarsson, Kalle \u00c5str\u00f6m, and Mark D. Fairchild. 2020. LIP: A Difference Evaluator for Alternating Images. ACM Comp. Graph. and Interactive Techn. 3, 2 (2020), 15:1--15:23."},{"key":"e_1_2_2_2_1","unstructured":"Hendrik Baatz Jonathan Granskog Marios Papas Fabrice Rousselle and Jan Nov\u00e1k."},{"key":"e_1_2_2_3_1","volume-title":"NeRF-Tex: Neural Reflectance Field Textures. In Eurographics Symp. Rend.","unstructured":"2021. NeRF-Tex: Neural Reflectance Field Textures. In Eurographics Symp. Rend."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570327"},{"key":"e_1_2_2_5_1","volume-title":"Srinivasan","author":"Barron Jonathan T.","year":"2021","unstructured":"Jonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, and Pratul P. Srinivasan. 2021. Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields. ICCV (2021)."},{"key":"e_1_2_2_6_1","volume-title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields. CVPR","author":"Barron Jonathan T.","year":"2022","unstructured":"Jonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan, and Peter Hedman. 2022. Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields. CVPR (2022)."},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1572769.1572795"},{"key":"e_1_2_2_8_1","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"Bishop Christopher M.","unstructured":"Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3151666.3151713"},{"key":"e_1_2_2_10_1","volume-title":"Ribeiro","author":"Branco Paula","year":"2016","unstructured":"Paula Branco, Lu\u00eds Torgo, and Rita P. Ribeiro. 2016. A Survey of Predictive Modeling on Imbalanced Domains. ACM Comput. Surv. 49, 2, Article 31 (2016)."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2011.81"},{"key":"e_1_2_2_12_1","volume-title":"Real-time Realistic Rendering and Lighting of Forests. Comp. Graph. Forum 31, 2pt1","author":"Bruneton Eric","year":"2012","unstructured":"Eric Bruneton and Fabrice Neyret. 2012. Real-time Realistic Rendering and Lighting of Forests. Comp. Graph. Forum 31, 2pt1 (2012), 373--382."},{"key":"e_1_2_2_13_1","volume-title":"Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, and Gordon Wetzstein.","author":"Chan Eric R.","year":"2021","unstructured":"Eric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano, Boxiao Pan, Shalini De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, and Gordon Wetzstein. 2021. Efficient Geometry-aware 3D Generative Adversarial Networks. In arXiv."},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276476"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.02063.x"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3507915"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3522735"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258849"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlppower-1.4"},{"key":"e_1_2_2_20_1","volume-title":"Eurographics Symp. Rend. 85--97","author":"Hasselgren Jon","year":"2021","unstructured":"Jon Hasselgren, Jacob Munkberg, Jaakko Lehtinen, Miika Aittala, and Samuli Laine. 2021. Appearance-Driven Automatic 3D Model Simplification. In Eurographics Symp. Rend. 85--97."},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766988"},{"key":"e_1_2_2_22_1","unstructured":"Eric Heitz and Fabrice Neyret. 2012. Representing Appearance and Pre-filtering Subpixel Data in Sparse Voxel Octrees. In High Perf. Graph. Carsten Dachsbacher Jacob Munkberg and Jacopo Pantaleoni (Eds.)."},{"key":"e_1_2_2_23_1","volume-title":"Light transport on path-space manifolds. Ph. D. Dissertation","author":"Jakob Wenzel","unstructured":"Wenzel Jakob. 2013. Light transport on path-space manifolds. Ph. D. Dissertation. Cornell University."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130880"},{"key":"e_1_2_2_25_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_2_26_1","volume-title":"Proc. Graph. Interface. 43--50","author":"Kobbelt Leif","year":"1998","unstructured":"Leif Kobbelt, Swen Campagna, and Hans-Peter Seidel. 1998. A General Framework for Mesh Decimation. In Proc. Graph. Interface. 43--50."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459795"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530721"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1289603.1289604"},{"key":"e_1_2_2_30_1","volume-title":"Int. Conf. Machine Learning. 2971--2980","author":"Lehtinen Jaakko","year":"2018","unstructured":"Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Samuli Laine, Tero Karras, Miika Aittala, and Timo Aila. 2018. Noise2Noise: Learning Image Restoration without Clean Data. In Int. Conf. Machine Learning. 2971--2980."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13138"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13346"},{"key":"e_1_2_2_33_1","unstructured":"Linjie Lyu Ayush Tewari Thomas Leimkuehler Marc Habermann and Christian Theobalt. 2022. Neural Radiance Transfer Fields for Relightable Novel-view Synthesis with Global Illumination. In ECCV."},{"key":"e_1_2_2_34_1","volume-title":"Introduction to Information Retrieval","author":"Manning Christopher D.","unstructured":"Christopher D. Manning, Prabhakar Raghavan, and Hinrich Sch\u00fctze. 2008. Introduction to Information Retrieval. Cambridge University Press."},{"key":"e_1_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul P. Srinivasan Matthew Tancik Jonathan T. Barron Ravi Ramamoorthi and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_2_36_1","unstructured":"Thomas M\u00fcller. 2021. tiny-cuda-nn. https:\/\/github.com\/NVlabs\/tiny-cuda-nn"},{"key":"e_1_2_2_37_1","volume-title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding. CoRR abs\/2201.05989","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. CoRR abs\/2201.05989 (2022)."},{"key":"e_1_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Ken Museth. 2021. NanoVDB: A GPU-Friendly and Portable VDB Data Structure For Real-Time Rendering And Simulation. In ACM SIGGRAPH Talks (SIGGRAPH). Article 1 2 pages.","DOI":"10.1145\/3450623.3464653"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480487"},{"key":"e_1_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Rolandos Potamias Stylianos Ploumpis and Stefanos Zafeiriou. 2022. Neural Mesh Simplification. 18562--18571.","DOI":"10.1109\/CVPR52688.2022.01803"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"e_1_2_2_42_1","volume-title":"Eurographics - Tutorials","author":"Puppo Enrico","unstructured":"Enrico Puppo and Roberto Scopigno. 1997. Simplification, LOD and Multiresolution Principles and Applications. In Eurographics - Tutorials. Eurographics Association."},{"key":"e_1_2_2_43_1","volume-title":"Neural Precomputed Radiance Transfer. Comp. Graph. Forum (Proc. Eurographics) 41, 2","author":"Rainer Gilles","year":"2022","unstructured":"Gilles Rainer, Adrien Bousseau, Tobias Ritschel, and George Drettakis. 2022. Neural Precomputed Radiance Transfer. Comp. Graph. Forum (Proc. Eurographics) 41, 2 (2022)."},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462009"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.02093.x"},{"key":"e_1_2_2_46_1","doi-asserted-by":"crossref","unstructured":"P.Y. Simard D. Steinkraus and J.C. Platt. 2003. Best practices for convolutional neural networks applied to visual document analysis. In Doc. Anal. and Recogn. 958--963.","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"e_1_2_2_47_1","volume-title":"Stupid Spherical Harmonics (SH) Tricks. Game Developers Conference (01","author":"Sloan Peter-Pike","year":"2008","unstructured":"Peter-Pike Sloan. 2008. Stupid Spherical Harmonics (SH) Tricks. Game Developers Conference (01 2008)."},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566612"},{"key":"e_1_2_2_49_1","volume-title":"Nerfplayer: A streamable dynamic scene representation with decomposed neural radiance fields","author":"Song Liangchen","year":"2023","unstructured":"Liangchen Song, Anpei Chen, Zhong Li, Zhang Chen, Lele Chen, Junsong Yuan, Yi Xu, and Andreas Geiger. 2023. Nerfplayer: A streamable dynamic scene representation with decomposed neural radiance fields. IEEE Transactions on Visualization and Computer Graphics (2023)."},{"key":"e_1_2_2_50_1","article-title":"Variable Bitrate Neural Fields. In ACM","author":"Takikawa Towaki","year":"2022","unstructured":"Towaki Takikawa, Alex Evans, Jonathan Tremblay, Thomas M\u00fcller, Morgan McGuire, Alec Jacobson, and Sanja Fidler. 2022. Variable Bitrate Neural Fields. In ACM Trans. Graph. Article 41.","journal-title":"Trans. Graph. Article 41."},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14507"},{"key":"e_1_2_2_52_1","volume-title":"Robust Monte Carlo Methods for Light Transport Simulation. Ph. D. Dissertation","author":"Veach Eric","unstructured":"Eric Veach. 1997. Robust Monte Carlo Methods for Light Transport Simulation. Ph. D. Dissertation. Stanford University."},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459815"},{"key":"e_1_2_2_54_1","article-title":"SpongeCake: A Layered Microflake Surface Appearance Model","volume":"42","author":"Wang Beibei","year":"2022","unstructured":"Beibei Wang, Wenhua Jin, Milo\u0161 Ha\u0161an, and Ling-Qi Yan. 2022a. SpongeCake: A Layered Microflake Surface Appearance Model. ACM Trans. Graph. 42, 1, Article 8 (2022).","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01316"},{"key":"e_1_2_2_56_1","volume-title":"Conf. App. Comp. Methods to Reactor Problems 557","author":"Woodcock E","year":"1965","unstructured":"E Woodcock. 1965. Techniques used in the GEM code for Monte Carlo neutronics calculations in reactors and other systems of complex geometry. Conf. App. Comp. Methods to Reactor Problems 557 (1965)."},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14505"},{"key":"e_1_2_2_58_1","volume-title":"Lightweight Neural Basis Functions for All-Frequency Shading. In SIGGRAPH Asia Conf. Papers (SA). Article 14","author":"Xu Zilin","year":"2022","unstructured":"Zilin Xu, Zheng Zeng, Lifan Wu, Lu Wang, and Ling-Qi Yan. 2022. Lightweight Neural Basis Functions for All-Frequency Shading. In SIGGRAPH Asia Conf. Papers (SA). Article 14, 9 pages."},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601155"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530105"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3592443","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3592443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:59Z","timestamp":1750182539000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3592443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,26]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10.1145\/3592443"],"URL":"https:\/\/doi.org\/10.1145\/3592443","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,26]]},"assertion":[{"value":"2023-07-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}