{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:04:57Z","timestamp":1784268297989,"version":"3.55.0"},"reference-count":39,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T00:00:00Z","timestamp":1698624000000},"content-version":"vor","delay-in-days":29,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100003661","name":"Korea Institute for Advancement of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["P0012746"],"award-info":[{"award-number":["P0012746"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We propose IBL\u2010NeRF, which decomposes the neural radiance fields (NeRF) of large\u2010scale indoor scenes into intrinsic components. Recent approaches further decompose the baked radiance of the implicit volume into intrinsic components such that one can partially approximate the rendering equation. However, they are limited to representing isolated objects with a shared environment lighting, and suffer from computational burden to aggregate rays with Monte Carlo integration. In contrast, our prefiltered radiance field extends the original NeRF formulation to capture the spatial variation of lighting within the scene volume, in addition to surface properties. Specifically, the scenes of diverse materials are decomposed into intrinsic components for rendering, namely, albedo, roughness, surface normal, irradiance, and prefiltered radiance. All of the components are inferred as neural images from MLP, which can model large\u2010scale general scenes. Especially the prefiltered radiance effectively models the volumetric light field, and captures spatial variation beyond a single environment light. The prefiltering aggregates rays in a set of predefined neighborhood sizes such that we can replace the costly Monte Carlo integration of global illumination with a simple query from a neural image. By adopting NeRF, our approach inherits superior visual quality and multi\u2010view consistency for synthesized images as well as the intrinsic components. We demonstrate the performance on scenes with complex object layouts and light configurations, which could not be processed in any of the previous works.<\/jats:p>","DOI":"10.1111\/cgf.14929","type":"journal-article","created":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T06:05:17Z","timestamp":1698732317000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["IBL\u2010NeRF: Image\u2010Based Lighting Formulation of Neural Radiance Fields"],"prefix":"10.1111","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5748-6003","authenticated-orcid":false,"given":"Changwoon","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering Seoul National University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6218-3426","authenticated-orcid":false,"given":"Juhyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering Seoul National University"},{"name":"Department of Computer Science Dartmouth College"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6735-8539","authenticated-orcid":false,"given":"Young Min","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering Seoul National University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,10,30]]},"reference":[{"key":"e_1_2_6_2_2","doi-asserted-by":"crossref","unstructured":"BossM. BraunR. JampaniV. BarronJ. T. LiuC. LenschH.: Nerd: Neural reflectance decomposition from image collections. InProceedings of the IEEE\/CVF International Conference on Computer Vision(2021) pp.12684\u201312694. 2","DOI":"10.1109\/ICCV48922.2021.01245"},{"key":"e_1_2_6_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601206"},{"key":"e_1_2_6_4_2","unstructured":"BitterliB.:Rendering resources 2016.https:\/\/benedikt-bitterli.me\/resources\/. 5"},{"key":"e_1_2_6_5_2","unstructured":"BossM. JampaniV. BraunR. LiuC. BarronJ. T. LenschH. P.: Neural-pil: Neural pre-integrated lighting for reflectance decomposition. InAdvances in Neural Information Processing Systems (NeurIPS)(2021). 2"},{"key":"e_1_2_6_6_2","unstructured":"BiS. XuZ. SrinivasanP. MildenhallB. SunkavalliK. Ha\u0161anM. Hold-GeoffroyY. KriegmanD. RamamoorthiR.: Neural reflectance fields for appearance acquisition.arXiv preprint arXiv:2008.03824(2020). 2 4 6"},{"key":"e_1_2_6_7_2","doi-asserted-by":"crossref","unstructured":"ChengL. ZhangC. LiaoZ.: Intrinsic image transformation via scale space decomposition. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2018) pp.656\u2013665. 2","DOI":"10.1109\/CVPR.2018.00075"},{"key":"e_1_2_6_8_2","doi-asserted-by":"crossref","unstructured":"DaiA. ChangA. X. SavvaM. HalberM. FunkhouserT. NiessnerM.: Scannet: Richly-annotated 3d reconstructions of indoor scenes. InProc. Computer Vision and Pattern Recognition (CVPR) IEEE(2017). 6","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_2_6_9_2","doi-asserted-by":"crossref","unstructured":"Duch\u00eaneS. RiantC. ChaurasiaG. Lopez-MorenoJ. LaffontP.-Y. PopovS. BousseauA. DrettakisG.: Multi-view intrinsic images of outdoors scenes with an application to relighting.ACM Transactions on Graphics(2015) 16. 2","DOI":"10.1145\/2756549"},{"key":"e_1_2_6_10_2","unstructured":"GuoY.-C. KangD. BaoL. HeY. ZhangS.-H.: Nerfren: Neural radiance fields with reflections.arXiv preprint arXiv:2111.15234(2021). 10"},{"key":"e_1_2_6_11_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03137.x"},{"key":"e_1_2_6_12_2","unstructured":"HasselgrenJ. HofmannN. MunkbergJ.: Shape Light and Material Decomposition from Images using Monte Carlo Rendering and Denoising.arXiv:2206.03380(2022). 2"},{"key":"e_1_2_6_13_2","doi-asserted-by":"crossref","unstructured":"KajiyaJ. T.: The rendering equation. InProceedings of the 13th annual conference on Computer graphics and interactive techniques(1986) pp.143\u2013150. 3","DOI":"10.1145\/15922.15902"},{"issue":"3","key":"e_1_2_6_14_2","article-title":"Real shading in unreal engine 4","volume":"4","author":"Karis B.","year":"2013","journal-title":"Proc. Physically Based Shading Theory Practice"},{"key":"e_1_2_6_15_2","unstructured":"KimJ. KimY. M.: Fast and Lightweight Path Guiding Algorithm on GPU. InPacific Graphics Short Papers Posters and Work-in-Progress Papers(2021) Lee S.-H. Zollmann S. Okabe M. W\u00fcnsche B. (Eds.) The Eurographics Association. doi:10.2312\/pg.20211379. 5"},{"key":"e_1_2_6_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366221"},{"key":"e_1_2_6_17_2","doi-asserted-by":"crossref","unstructured":"LiZ. SnavelyN.: Cgintrinsics: Better intrinsic image decomposition through physically-based rendering. InProceedings of the European Conference on Computer Vision (ECCV)(2018) pp.371\u2013387. 2","DOI":"10.1007\/978-3-030-01219-9_23"},{"key":"e_1_2_6_18_2","doi-asserted-by":"crossref","unstructured":"LiZ. SnavelyN.: Learning intrinsic image decomposition from watching the world. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2018) pp.9039\u20139048. 2","DOI":"10.1109\/CVPR.2018.00942"},{"key":"e_1_2_6_19_2","doi-asserted-by":"crossref","unstructured":"LiZ. ShafieiM. RamamoorthiR. SunkavalliK. ChandrakerM.: Inverse rendering for complex indoor scenes: Shape spatially-varying lighting and svbrdf from a single image. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2020) pp.2475\u20132484. 2","DOI":"10.1109\/CVPR42600.2020.00255"},{"key":"e_1_2_6_20_2","doi-asserted-by":"crossref","unstructured":"LiZ. WangL. ChengM. PanC. YangJ.: Multi-view inverse rendering for large-scale real-world indoor scenes. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2023). 2","DOI":"10.1109\/CVPR52729.2023.01203"},{"key":"e_1_2_6_21_2","doi-asserted-by":"crossref","unstructured":"MaW.-C. ChuH. ZhouB. UrtasunR. TorralbaA.: Single image intrinsic decomposition without a single intrinsic image. InProceedings of the European Conference on Computer Vision (ECCV)(2018) pp.201\u2013217. 2","DOI":"10.1007\/978-3-030-01264-9_13"},{"key":"e_1_2_6_22_2","doi-asserted-by":"crossref","unstructured":"MildenhallB. SrinivasanP. P. TancikM. BarronJ. T. RamamoorthiR. NgR.: Nerf: Representing scenes as neural radiance fields for view synthesis. InEuropean conference on computer vision(2020) Springer pp.405\u2013421. 1 2 6","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_6_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3374753"},{"key":"e_1_2_6_24_2","doi-asserted-by":"crossref","unstructured":"OechsleM. PengS. GeigerA.: Unisurf: Unifying neural implicit surfaces and radiance fields for multi-view reconstruction. InProceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)(October2021) pp.5589\u20135599. 9","DOI":"10.1109\/ICCV48922.2021.00554"},{"key":"e_1_2_6_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778803"},{"key":"e_1_2_6_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459872"},{"key":"e_1_2_6_26_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/3450626.3459872. 2","DOI":"10.1145\/3450626.3459872"},{"key":"e_1_2_6_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469842"},{"key":"e_1_2_6_27_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/3469842. 2","DOI":"10.1145\/3469842"},{"key":"e_1_2_6_28_2","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) pp.7495\u20137504. 2 4 5 6"},{"key":"e_1_2_6_29_2","doi-asserted-by":"crossref","unstructured":"SchonbergerJ. L. FrahmJ.-M.: Structure-from-motion revisited. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(June2016). 6","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_2_6_30_2","doi-asserted-by":"crossref","unstructured":"SenguptaS. GuJ. KimK. LiuG. JacobsD. W. KautzJ.: Neural inverse rendering of an indoor scene from a single image. InProceedings of the IEEE\/CVF International Conference on Computer Vision(2019) pp.8598\u20138607. 2","DOI":"10.1109\/ICCV.2019.00869"},{"key":"e_1_2_6_31_2","doi-asserted-by":"crossref","unstructured":"VerbinD. HedmanP. MildenhallB. ZicklerT. BarronJ. T. SrinivasanP. P.: Ref-NeRF: Structured view-dependent appearance for neural radiance fields.CVPR(2022). 2","DOI":"10.1109\/CVPR52688.2022.00541"},{"key":"e_1_2_6_32_2","first-page":"27171","volume-title":"Advances in Neural Information Processing Systems","author":"Wang P.","year":"2021"},{"key":"e_1_2_6_33_2","doi-asserted-by":"crossref","unstructured":"WeiY. LiuS. RaoY. ZhaoW. LuJ. ZhouJ.: Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo. InProceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)(October2021) pp.5610\u20135619. 6","DOI":"10.1109\/ICCV48922.2021.00556"},{"key":"e_1_2_6_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6961"},{"key":"e_1_2_6_35_2","doi-asserted-by":"crossref","unstructured":"ZhuJ. HuoY. YeQ. LuanF. LiJ. XiD. WangL. TangR. HuaW. BaoH. et al.: I2-sdf: Intrinsic indoor scene reconstruction and editing via raytracing in neural sdfs. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2023) pp.12489\u201312498. 2","DOI":"10.1109\/CVPR52729.2023.01202"},{"key":"e_1_2_6_36_2","doi-asserted-by":"crossref","unstructured":"ZhouT. KrahenbuhlP. EfrosA. A.: Learning data-driven reflectance priors for intrinsic image decomposition. InProceedings of the IEEE International Conference on Computer Vision(2015) pp.3469\u20133477. 2 9","DOI":"10.1109\/ICCV.2015.396"},{"key":"e_1_2_6_37_2","doi-asserted-by":"crossref","unstructured":"ZhangK. LuanF. WangQ. BalaK. SnavelyN.: Physg: Inverse rendering with spherical gaussians for physics-based material editing and relighting. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2021) pp.5453\u20135462. 2","DOI":"10.1109\/CVPR46437.2021.00541"},{"key":"e_1_2_6_38_2","doi-asserted-by":"crossref","unstructured":"ZhangX. SrinivasanP. P. DengB. DebevecP. FreemanW. T. BarronJ. T.: Nerfactor: Neural factorization of shape and reflectance under an unknown illumination.arXiv:2106.01970(2021). 2 4 5 6","DOI":"10.1145\/3478513.3480496"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T02:43:31Z","timestamp":1730429011000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.14929"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":39,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["10.1111\/cgf.14929"],"URL":"https:\/\/doi.org\/10.1111\/cgf.14929","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]},"assertion":[{"value":"2023-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e14929"}}