{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:38:58Z","timestamp":1786534738107,"version":"3.56.0"},"reference-count":82,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"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>Volumetric inverse rendering seeks to recover the optical properties of participating media from images. Existing approaches either rely on differentiable stochastic light transport simulation, which require substantial algorithmic effort, or use simplified models that fail to capture global illumination. We propose a formulation that reconciles physically complete light transport with general\u2010purpose neural optimization. The optical properties of the medium and the full light field are represented as neural fields and estimated through a joint optimization process. Global illumination is enforced via a residual objective derived from the Radiative Transfer Equation in local differential form, complemented by a volume rendering term along primary viewing rays to mitigate low\u2010frequency bias. We demonstrate reconstruction of spatially varying, color\u2010resolved scattering, absorption, and phase function parameters from multi\u2010view images. Beyond reconstruction, the same framework supports learning generative models of participating media with physical optical properties under global illumination.<\/jats:p>","DOI":"10.1111\/cgf.70541","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:10:55Z","timestamp":1786533055000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Volumetric Inverse Rendering via Neural Radiative Transfer"],"prefix":"10.1111","author":[{"given":"Ntumba Elie","family":"Nsampi","sequence":"first","affiliation":[{"name":"Max\u2010Planck\u2010Institut f\u00fcr Informatik"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adarsh","family":"Djeacoumar","sequence":"additional","affiliation":[{"name":"Max\u2010Planck\u2010Institut f\u00fcr Informatik"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans\u2010Peter","family":"Seidel","sequence":"additional","affiliation":[{"name":"Max\u2010Planck\u2010Institut f\u00fcr Informatik"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Ritschel","sequence":"additional","affiliation":[{"name":"University College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Leimk\u00fchler","sequence":"additional","affiliation":[{"name":"Max\u2010Planck\u2010Institut f\u00fcr Informatik"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"key":"e_1_2_8_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0149-1970(01)00023-3"},{"key":"e_1_2_8_3_2","unstructured":"AzinovicD. LiT.\u2010M. KaplanyanA. NiessnerM.: Inverse path tracing for joint material and lighting estimation. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition(2019) pp.2447\u20132456. 6"},{"key":"e_1_2_8_4_2","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/21\/5\/002"},{"key":"e_1_2_8_5_2","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/24\/3\/034011"},{"key":"e_1_2_8_6_2","first-page":"10691","article-title":"Neural\u2010pil: Neural pre\u2010integrated lighting for reflectance decomposition","volume":"34","author":"Boss M.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_7_2","unstructured":"BiS. XuZ. SrinivasanP. MildenhallB. SunkavalliK. Ha\u0161anM. Hold\u2010GeoffroyY. KriegmanD. RamamoorthiR.: Neural reflectance fields for appearance acquisition.arXiv preprint arXiv:2008.03824(2020). 3"},{"key":"e_1_2_8_8_2","doi-asserted-by":"crossref","unstructured":"ChenR. ChenY. JiaoN. JiaK.: Fantasia3d: Disentangling geometry and appearance for high\u2010quality text\u2010to\u20103d content creation. InProceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)(October2023) pp.22246\u201322256. 3","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_2_8_9_2","doi-asserted-by":"crossref","unstructured":"ChenH. GuJ. ChenA. TianW. TuZ. LiuL. SuH.: Single\u2010stage diffusion nerf: A unified approach to 3d generation and reconstruction. InProceedings of the IEEE\/CVF international conference on computer vision(2023) pp.2416\u20132425. 3","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"e_1_2_8_10_2","volume-title":"Radiative Transfer","author":"Chandrasekhar S.","year":"1960"},{"key":"e_1_2_8_11_2","unstructured":"ChanE. R. LinC. Z. ChanM. A. NaganoK. PanB. De MelloS. GalloO. GuibasL. J. TremblayJ. KhamisS. et al.: Efficient geometry\u2010aware 3d generative adversarial networks. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition(2022) pp.16123\u201316133. 3"},{"key":"e_1_2_8_12_2","first-page":"1","volume-title":"2020 IEEE International Conference on Computational Photography (ICCP)","author":"Che C.","year":"2020"},{"key":"e_1_2_8_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530169"},{"key":"e_1_2_8_14_2","unstructured":"ChenH. LinZ. ZhangJ.: Gi\u2010gs: Global illumination decomposition on gaussian splatting for inverse rendering. InProceedings of the International Conference on Learning Representations (ICLR)(2025). 3"},{"key":"e_1_2_8_15_2","doi-asserted-by":"crossref","unstructured":"DengX. LuanF. WalterB. BalaK. MarschnerS.: Reconstructing translucent objects using differentiable rendering. InACM SIGGRAPH 2022 Conference Proceedings(2022) pp.1\u201310. 3","DOI":"10.1145\/3528233.3530714"},{"key":"e_1_2_8_16_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3870"},{"key":"e_1_2_8_17_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14846"},{"key":"e_1_2_8_18_2","doi-asserted-by":"crossref","unstructured":"DengX. WuL. WalterB. RamamoorthiR. d'EonE. MarschnerS. WeidlichA.: Reconstructing translucent thin objects from photos. InSIGGRAPH Asia 2024 Conference Papers(2024) pp.1\u201311. 3","DOI":"10.1145\/3680528.3687572"},{"key":"e_1_2_8_19_2","doi-asserted-by":"crossref","unstructured":"FanJ. LuanF. YangJ. HasanM. WangB.: Rng: Relightable neural gaussians.Proceedings of CVPR 2025(2025). 3","DOI":"10.1109\/CVPR52734.2025.02470"},{"key":"e_1_2_8_20_2","first-page":"685","volume-title":"European Conference on Computer Vision","author":"Gkioulekas I.","year":"2016"},{"key":"e_1_2_8_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508377"},{"key":"e_1_2_8_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480569"},{"key":"e_1_2_8_23_2","doi-asserted-by":"publisher","DOI":"10.1086\/144246"},{"key":"e_1_2_8_24_2","doi-asserted-by":"crossref","unstructured":"HadadanS. LinG. Nov\u00e1kJ. RousselleF. ZwickerM.: Inverse global illumination using a neural radiometric prior. InACM SIGGRAPH 2023 Conference Proceedings(2023) pp.1\u201311. 2 3","DOI":"10.1145\/3588432.3591553"},{"key":"e_1_2_8_25_2","doi-asserted-by":"crossref","unstructured":"HenzlerP. MitraN. J. RitschelT.: Escaping plato's cave: 3d shape from adversarial rendering. InProceedings of the IEEE\/CVF International Conference on Computer Vision(2019) pp.9984\u20139993. 3","DOI":"10.1109\/ICCV.2019.01008"},{"key":"e_1_2_8_26_2","article-title":"Gans trained by a two time\u2010scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel M.","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"e_1_2_8_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597300"},{"key":"e_1_2_8_28_2","doi-asserted-by":"crossref","unstructured":"JinH. LiuI. XuP. ZhangX. HanS. BiS. ZhouX. XuZ. SuH.: Tensoir: Tensorial inverse rendering. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2023) pp.165\u2013174. 3 7","DOI":"10.1109\/CVPR52729.2023.00024"},{"key":"e_1_2_8_29_2","unstructured":"KingmaD. P. BaJ.: Adam: A method for stochastic optimization. InInternational Conference on Learning Representations (ICLR)(2015). 6"},{"key":"e_1_2_8_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.matcom.2019.01.010"},{"key":"e_1_2_8_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_2_8_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130880"},{"key":"e_1_2_8_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/964965.808594"},{"key":"e_1_2_8_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275055"},{"key":"e_1_2_8_35_2","doi-asserted-by":"crossref","unstructured":"LevisA. SchechnerY. Y. AidesA. DavisA. B.: Airborne three\u2010dimensional cloud tomography. InProceedings of the IEEE International Conference on Computer Vision(2015) pp.3379\u20133387. 3","DOI":"10.1109\/ICCV.2015.386"},{"key":"e_1_2_8_36_2","unstructured":"LevisA. SchechnerY. Y. DavisA. B.: Multiple\u2010scattering microphysics tomography. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2017) pp.6740\u20136749. 3"},{"key":"e_1_2_8_37_2","doi-asserted-by":"crossref","unstructured":"LyuL. TewariA. Leimk\u00fchlerT. HabermannM. TheobaltC.: Neural radiance transfer fields for relightable novel\u2010view synthesis with global illumination. InECCV(2022). 3","DOI":"10.1007\/978-3-031-19790-1_10"},{"issue":"4","key":"e_1_2_8_38_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3658211","article-title":"Tensosdf: Roughness\u2010aware tensorial representation for robust geometry and material reconstruction","volume":"43","author":"Li J.","year":"2024","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_8_39_2","doi-asserted-by":"crossref","unstructured":"LiangZ. ZhangQ. FengY. ShanY. JiaK.: Gsir: 3d gaussian splatting for inverse rendering. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2024) pp.21644\u201321653. 3","DOI":"10.1109\/CVPR52733.2024.02045"},{"key":"e_1_2_8_40_2","doi-asserted-by":"publisher","DOI":"10.13182\/NSE112-185"},{"key":"e_1_2_8_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_2_8_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jqsrt.2021.107705"},{"key":"e_1_2_8_43_2","doi-asserted-by":"crossref","unstructured":"M\u00fcllerN. SiddiquiY. PorziL. BuloS. R. KontschiederP. NiessnerM.: Diffrf: Rendering\u2010guided 3d radiance field diffusion. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2023). 3","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"e_1_2_8_44_2","first-page":"405","volume-title":"European Conference on Computer Vision","author":"Mildenhall B.","year":"2020"},{"key":"e_1_2_8_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530073"},{"key":"e_1_2_8_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392406"},{"key":"e_1_2_8_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356498"},{"key":"e_1_2_8_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592139"},{"key":"e_1_2_8_49_2","doi-asserted-by":"crossref","unstructured":"ParkJ. J. FlorenceP. StraubJ. NewcombeR. LovegroveS.: Deepsdf: Learning continuous signed distance functions for shape representation. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition(2019) pp.165\u2013174. 6","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_2_8_50_2","unstructured":"PaszkeA. GrossS. ChintalaS. ChananG. YangE. DeVitoZ. LinZ. DesmaisonA. AntigaL. LererA.:Automatic differentiation in pytorch. 6"},{"key":"e_1_2_8_51_2","volume-title":"Physically based rendering: From theory to implementation","author":"Pharr M.","year":"2023"},{"key":"e_1_2_8_52_2","first-page":"11","volume-title":"Eurographics Workshop on Rendering Techniques","author":"Pauly M.","year":"2000"},{"key":"e_1_2_8_53_2","unstructured":"Poly Haven:Poly haven: The public 3d asset library 2026. URL:https:\/\/polyhaven.com\/. 7"},{"key":"e_1_2_8_54_2","first-page":"20002","article-title":"A shading\u2010guided generative implicit model for shape\u2010accurate 3d\u2010aware image synthesis","volume":"34","author":"Pan X.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_55_2","first-page":"5301","volume-title":"International conference on machine learning","author":"Rahaman N.","year":"2019"},{"key":"e_1_2_8_56_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0167155"},{"key":"e_1_2_8_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"e_1_2_8_58_2","doi-asserted-by":"crossref","unstructured":"SrinivasanP. P. DengB. ZhangX. TancikM. MildenhallB. BarronJ. T.: Nerv: Neural reflectance and visibility fields for relighting and view synthesis. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition(2021). 2 3","DOI":"10.1109\/CVPR46437.2021.00741"},{"key":"e_1_2_8_59_2","first-page":"7462","article-title":"Implicit neural representations with periodic activation functions","volume":"33","author":"Sitzmann V.","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"e_1_2_8_60_2","article-title":"Light field networks: Neural scene representations with single\u2010evaluation rendering","volume":"34","author":"Sitzmann V.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_61_2","unstructured":"StamnesK. TsayS.\u2010C. WiscombeW. LaszloI.:Disort a general\u2010purpose fortran program for discrete\u2010ordinate\u2010method radiative transfer in scattering and emitting layered media: documentation of methodology. 3"},{"key":"e_1_2_8_62_2","doi-asserted-by":"crossref","unstructured":"ShiY. WuY. WuC. LiuX. ZhaoC. FengH. ZhangJ. ZhouB. DingE. WangJ.: Gir: 3d gaussian inverse rendering for relightable scene factorization.IEEE Transactions on Transactions on Pattern Analysis and Machine Intelligence(2025). 3","DOI":"10.1109\/TPAMI.2025.3575937"},{"key":"e_1_2_8_63_2","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"33","author":"Tancik M.","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"e_1_2_8_64_2","article-title":"Physically\u2010based lighting for 3d generative models of cars","volume":"43","author":"Violante N.","year":"2024","journal-title":"Computer Graphics Forum (Proceedings of the Eurographics Conference)"},{"issue":"4","key":"e_1_2_8_65_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459804","article-title":"Path replay backpropagation: Differentiating light paths using constant memory and linear time","volume":"40","author":"Vicini D.","year":"2021","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_8_66_2","doi-asserted-by":"crossref","unstructured":"WuS. BasuS. BroedermannT. Van GoolL. SakaridisC.: Pbr\u2010nerf: Inverse rendering with physics\u2010based neural fields. InProceedings of the Computer Vision and Pattern Recognition Conference(2025) pp.10974\u201310984. 3","DOI":"10.1109\/CVPR52734.2025.01025"},{"key":"e_1_2_8_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_8_68_2","unstructured":"WorchelM. FinnendahlU. AlexaM.: Radiative back\u2010propagation with non\u2010static geometry. InProc. EGSR(2025). 3"},{"key":"e_1_2_8_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3730855"},{"key":"e_1_2_8_70_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110768"},{"key":"e_1_2_8_71_2","first-page":"641","volume-title":"Computer graphics forum","author":"Xie Y.","year":"2022"},{"key":"e_1_2_8_72_2","article-title":"Inferring hybrid neural fluid fields from videos","volume":"36","author":"Yu H.\u2010X.","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_73_2","first-page":"700","volume-title":"European conference on computer vision","author":"Yao Y.","year":"2022"},{"key":"e_1_2_8_74_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jqsrt.2024.109253"},{"key":"e_1_2_8_75_2","doi-asserted-by":"crossref","unstructured":"ZhangR. IsolaP. EfrosA. A. ShechtmanE. WangO.: The unreasonable effectiveness of deep features as a perceptual metric. InProceedings of the IEEE conference on computer vision and pattern recognition(2018) pp.586\u2013595. 7","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_8_76_2","doi-asserted-by":"crossref","unstructured":"ZhangK. LuanF. WangQ. BalaK. SnavelyN.: Physg: Inverse rendering with spherical gaussians for physics\u2010based material editing and relighting. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition(2021) pp.5453\u20135462. 3","DOI":"10.1109\/CVPR46437.2021.00541"},{"issue":"4","key":"e_1_2_8_77_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3658170","article-title":"Dreammat: High\u2010quality pbr material generation with geometry\u2010and light\u2010aware diffusion models","volume":"43","author":"Zhang Y.","year":"2024","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_8_78_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14337"},{"key":"e_1_2_8_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459807"},{"key":"e_1_2_8_80_2","article-title":"Neural relightable participating media rendering","volume":"34","author":"Zheng Q.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356566"},{"key":"e_1_2_8_82_2","doi-asserted-by":"crossref","unstructured":"ZhangY. XuT. YuJ. YeY. JingY. WangJ. YuJ. YangW.: Nemf: Inverse volume rendering with neural microflake field. InProceedings of the IEEE\/CVF International Conference on Computer Vision(2023). 2 3","DOI":"10.1109\/ICCV51070.2023.02095"},{"issue":"4","key":"e_1_2_8_83_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459782","article-title":"Path\u2010space differentiable rendering of participating media","volume":"40","author":"Zhang C.","year":"2021","journal-title":"ACM Transactions on Graphics (TOG)"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70541","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70541","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:11:10Z","timestamp":1786533070000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70541"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":82,"alternative-id":["10.1111\/cgf.70541"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70541","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]},"assertion":[{"value":"2026-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70541"}}