{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:39:55Z","timestamp":1786621195936,"version":"3.56.0"},"reference-count":63,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Neural implicit surfaces are a powerful tool for encoding a surface as the zero level set of a neural function. Trained using gradient\u2010descent based optimizers, these methods however suffer from a low\u2010frequency bias that prevents them to fit fine details of the surface. Solutions to break this bias exist but often damage the regularity of the long range implicit function, making geometrical queries more difficult. In this work, we combine a 1\u2010Lipschitz neural function with a detail field made of compactly supported radial basis functions. While the neural function handles long\u2010range queries with low surface accuracy, the detail field is fitted to perturb the neural function so that its zero level set precisely goes through sampled points of the surface and locally accounts for small\u2010scale details. As it is compactly supported, regions where the 1\u2010Lipschitz property breaks are finely controlled. We therefore achieve the best of both worlds by greatly increasing the representation power of the implicit function near the zero level set while maintaining robustness far from the zero level set.<\/jats:p>","DOI":"10.1111\/cgf.70526","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:21:31Z","timestamp":1786620091000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Compactly supported detail field for high quality neural implicit surfaces"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5324-5122","authenticated-orcid":false,"given":"Guillaume","family":"Coiffier","sequence":"first","affiliation":[{"name":"Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8868-9644","authenticated-orcid":false,"given":"Justine","family":"Basselin","sequence":"additional","affiliation":[{"name":"Independent researcher"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"e_1_2_7_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2001.964489"},{"key":"e_1_2_7_3_2","unstructured":"AraujoA. HavensA. DelattreB. AllauzenA. HuB.:A Unified Algebraic Perspective on Lipschitz Neural Networks Oct.2023. arXiv:2303.03169. 4"},{"key":"e_1_2_7_4_2","volume-title":"Introduction to Implicit Surfaces","author":"Bloomenthal J.","year":"1997"},{"key":"e_1_2_7_5_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018932227617"},{"key":"e_1_2_7_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201337"},{"key":"e_1_2_7_7_2","first-page":"685","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Basri R.","year":"2020"},{"key":"e_1_2_7_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/357306.357310"},{"key":"e_1_2_7_9_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492000015"},{"key":"e_1_2_7_10_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15128"},{"key":"e_1_2_7_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383266"},{"key":"e_1_2_7_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/964965.808602"},{"key":"e_1_2_7_13_2","doi-asserted-by":"publisher","DOI":"10.1137\/0907043"},{"key":"e_1_2_7_14_2","unstructured":"DaviesT. NowrouzezahraiD. JacobsonA.:On the Effectiveness of Weight\u2010Encoded Neural Implicit 3D Shapes Jan.2021. arXiv:2009.09808 doi:10.48550\/arXiv.2009.09808. 2"},{"key":"e_1_2_7_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0086566"},{"key":"e_1_2_7_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/1185657.1185675"},{"key":"e_1_2_7_17_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13951"},{"key":"e_1_2_7_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/0021\u20109991(87)90140\u20109"},{"key":"e_1_2_7_19_2","unstructured":"GroppA. YarivL. HaimN. AtzmonM. LipmanY.:Implicit Geometric Regularization for Learning Shapes July2020. arXiv:2002.10099. 2 7"},{"key":"e_1_2_7_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s003710050084"},{"key":"e_1_2_7_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322994"},{"key":"e_1_2_7_22_2","unstructured":"KingmaD. P. BaJ.: Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980(2014). 2"},{"key":"e_1_2_7_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/1361192.1361195"},{"key":"e_1_2_7_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37422"},{"key":"e_1_2_7_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010662\u201007443\u20105_3"},{"key":"e_1_2_7_26_2","unstructured":"LingS. MadanA. SharpN. JacobsonA.:Uniform Sampling of Surfaces by Casting Rays June2025. arXiv:2506.05268 doi:10.48550\/arXiv.2506.05268. 3"},{"key":"e_1_2_7_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2016.05.001"},{"key":"e_1_2_7_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384538"},{"key":"e_1_2_7_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_2_7_30_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467\u20108659.2010.01785.x"},{"key":"e_1_2_7_31_2","unstructured":"McGinnisJ. H\u00f6lzlF. A. ShitS. BiederF. FriedrichP. M\u00fchlauM. MenzeB. RueckertD. WiestlerB.:Optimizing Rank for High\u2010Fidelity Implicit Neural Representations Dec.2025. arXiv:2512.14366 doi:10.48550\/arXiv.2512.14366. 6"},{"key":"e_1_2_7_32_2","doi-asserted-by":"crossref","unstructured":"MeschederL. OechsleM. NiemeyerM. NowozinS. GeigerA.:Occupancy Networks: Learning 3D Reconstruction in Function Space Apr.2019. arXiv:1812.03828. 2","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_2_7_33_2","unstructured":"Muon:An optimizer for hidden layers in neural networks | Keller Jordan blog.https:\/\/kellerjordan.github.io\/posts\/muon\/. 6"},{"key":"e_1_2_7_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/1198555.1198645"},{"key":"e_1_2_7_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882293"},{"key":"e_1_2_7_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/0021\u20109991(88)90002\u20102"},{"key":"e_1_2_7_37_2","doi-asserted-by":"crossref","unstructured":"ParkJ. J. FlorenceP. StraubJ. NewcombeR. LovegroveS.:DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation Jan.2019. arXiv:1901.05103 doi:10.48550\/arXiv.1901.05103. 2","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_2_7_38_2","article-title":"Pytorch: An imperative style, high\u2010performance deep learning library","volume":"32","author":"Paszke A.","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"e_1_2_7_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00366\u2010010\u20100199\u20101"},{"key":"e_1_2_7_40_2","unstructured":"QuilezI.:3d sdf functions.https:\/\/iquilezles.org\/articles\/distfunctions\/. Accessed: 2026\u201004\u201006. 1"},{"key":"e_1_2_7_41_2","first-page":"5301","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Rahaman N.","year":"2019"},{"key":"e_1_2_7_42_2","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/16.2.157"},{"key":"e_1_2_7_43_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.93.4.1591"},{"key":"e_1_2_7_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530155"},{"key":"e_1_2_7_45_2","first-page":"7462","volume-title":"Advances in Neural Information Processing Systems","author":"Sitzmann V.","year":"2020"},{"key":"e_1_2_7_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00057"},{"key":"e_1_2_7_47_2","unstructured":"Stanford 3d scanning repository.http:\/\/graphics.stanford.edu\/data\/3Dscanrep\/. Accessed: 2026\u201004\u201013. 6"},{"key":"e_1_2_7_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01120"},{"key":"e_1_2_7_49_2","doi-asserted-by":"crossref","unstructured":"TurkG. O'BrienJ. F.: Shape Transformation Using Variational Implicit Functions. InProceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques \u2010 SIGGRAPH '99(1999) pp.335\u2013342. arXiv:2303.02937 doi:10.1145\/311535.311580. 2","DOI":"10.1145\/311535.311580"},{"key":"e_1_2_7_50_2","doi-asserted-by":"crossref","unstructured":"ToborI. ReuterP. SchlickC.: Multi\u2010scale reconstruction of implicit surfaces with attributes from large unorganized point sets. InProceedings Shape Modeling Applications 2004. (June2004) pp.19\u201330. doi:10.1109\/SMI.2004.1314490. 2","DOI":"10.1109\/SMI.2004.1314490"},{"key":"e_1_2_7_51_2","first-page":"7537","volume-title":"Advances in Neural Information Processing Systems","author":"Tancik M.","year":"2020"},{"key":"e_1_2_7_52_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010019\u20100686\u20102"},{"key":"e_1_2_7_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02123482"},{"key":"e_1_2_7_54_2","doi-asserted-by":"publisher","DOI":"10.1111\/1467\u20108659.00365"},{"key":"e_1_2_7_55_2","doi-asserted-by":"crossref","unstructured":"WeidemaierS. HartwigF. SassenJ. ContiS. BenChenM. RumpfM.: SDFs from Unoriented Point Clouds using Neural Variational Heat Distances.Computer Graphics Forum n\/a n\/a e70296. doi:10.1111\/cgf.70296. 2","DOI":"10.1111\/cgf.70296"},{"key":"e_1_2_7_56_2","doi-asserted-by":"crossref","unstructured":"WangP.\u2010S. LiuY. YangY.\u2010Q. TongX.:Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields Oct.2021. arXiv:2106.01553 doi:10.48550\/arXiv.2106.01553. 3","DOI":"10.24963\/ijcai.2021\/151"},{"key":"e_1_2_7_57_2","doi-asserted-by":"crossref","unstructured":"WangZ. WangC. YoshinoT. TaoS. FuZ. LiT.\u2010M.: HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2025) pp.1276\u20131286. 2 7 8","DOI":"10.1109\/CVPR52734.2025.00127"},{"key":"e_1_2_7_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3731191"},{"key":"e_1_2_7_59_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14505"},{"key":"e_1_2_7_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010030\u201036708\u20104_22"},{"key":"e_1_2_7_61_2","unstructured":"Yahoojapan 3d models.https:\/\/www.thingiverse.com\/YahooJAPAN\/designs. Accessed: 2026\u201004\u201013. 6"},{"key":"e_1_2_7_62_2","unstructured":"YifanW. RahmannL. Sorkine\u2010HornungO.:Geometry\u2010Consistent Neural Shape Representation with Implicit Displacement Fields Feb.2022. arXiv:2106.05187 doi:10.48550\/arXiv.2106.05187. 3 7 8 9"},{"key":"e_1_2_7_63_2","unstructured":"ZhouQ. JacobsonA.: Thingi10k: A dataset of 10 000 3d\u2010printing models.arXiv preprint arXiv:1605.04797(2016). 6 9"},{"key":"e_1_2_7_64_2","unstructured":"ZhengJ. RamasingheS. LuceyS.:Rethinking Positional Encoding Oct.2021. arXiv:2107.02561 doi:10.48550\/arXiv.2107.02561. 3"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70526","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70526","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:21:41Z","timestamp":1786620101000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70526"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":63,"alternative-id":["10.1111\/cgf.70526"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70526","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]},"assertion":[{"value":"2026-08-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70526"}}