{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T13:57:09Z","timestamp":1775829429866,"version":"3.50.1"},"reference-count":79,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"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>Despite recent advances in text\u2010to\u2010image generation, controlling geometric layout and PBR material properties in synthesized scenes remains challenging. We present a pipeline that first produces a G\u2010buffer (albedo, normals, depth, roughness, shading, and metallic) from a text prompt and then renders a final image through a PBR\u2010inspired branch network. This intermediate representation enables fine\u2010grained control: users can copy and paste within specific G\u2010buffer channels to insert or reposition objects, or apply masks to the irradiance channel to adjust lighting locally. As a result, real objects can be seamlessly integrated into virtual scenes. By separating user\u2010friendly scene description from image rendering, our method offers a practical balance between detailed post\u2010generation control and efficient text\u2010driven synthesis. We demonstrate its effectiveness through quantitative evaluations and a user study with 156 participants, showing consistent human preference over strong baselines and confirming that G\u2010buffer control extends the flexibility of text\u2010guided image generation.<\/jats:p>","DOI":"10.1111\/cgf.70329","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T13:09:43Z","timestamp":1775826583000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PBR\u2010Inspired Controllable Diffusion for Image Generation"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6628-577X","authenticated-orcid":false,"given":"Bowen","family":"Xue","sequence":"first","affiliation":[{"name":"University of Manchester  UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7703-5194","authenticated-orcid":false,"given":"Giuseppe Claudio","family":"Guarnera","sequence":"additional","affiliation":[{"name":"University of York  UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4759-0514","authenticated-orcid":false,"given":"Shuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana\u2010Champaign  USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0398-3105","authenticated-orcid":false,"given":"Zahra","family":"Montazeri","sequence":"additional","affiliation":[{"name":"University of Manchester  UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,4,10]]},"reference":[{"key":"e_1_2_8_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383309"},{"key":"e_1_2_8_2_3","unstructured":"url:https:\/\/doi.org\/10.1145\/383259.3833092."},{"key":"e_1_2_8_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601206"},{"key":"e_1_2_8_4_2","unstructured":"Battaglia Peter Hamrick Jessica Blake Chandler Bapst Victor et al. \u201cRelational inductive biases deep learning and graph networks\u201d.arXiv(2018). url:https:\/\/arxiv.org\/pdf\/1806.01261.pdf4."},{"key":"e_1_2_8_5_2","doi-asserted-by":"crossref","unstructured":"Barron Jonathan T. Mildenhall Ben Verbin Dor et al. \u201cMip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields\u201d.2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2022 5460\u20135469. doi:10.1109\/CVPR52688.2022.005392.","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_2_8_6_2","unstructured":"Barrow Harry G.andTenenbaum Jay M.\u201cRECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES\u201d.1978. url:https:\/\/api.semanticscholar.org\/CorpusID:148920072."},{"key":"e_1_2_8_7_2","unstructured":"Burley Brent. \u201cPhysically-Based Shading at Disney\u201d.2012. url:https:\/\/api.semanticscholar.org\/CorpusID:72601372."},{"key":"e_1_2_8_8_2","unstructured":"Chen Xi Huang Lianghua Liu Yu et al. \u201cAny-door: Zero-shot object-level image customization\u201d.arXiv preprint arXiv:2307.09481(2023) 3."},{"key":"e_1_2_8_9_2","volume-title":"Elements of information theory","author":"Cover Thomas M.","year":"1999"},{"key":"e_1_2_8_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/357290.357293"},{"key":"e_1_2_8_10_3","unstructured":"url:https:\/\/doi.org\/10.1145\/357290.3572934."},{"key":"e_1_2_8_11_2","unstructured":"Couairon Guillaume Verbeek Jakob Schwenk Holger andCord Matthieu.DiffEdit: Diffusion-based semantic image editing with mask guidance.2022. arXiv: 2210.11427 [cs.CV]. url:https:\/\/arxiv.org\/abs\/2210.114273."},{"key":"e_1_2_8_12_2","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Dhariwal Prafulla","year":"2021"},{"key":"e_1_2_8_13_2","article-title":"OutCast: Single Image Relighting with Cast Shadows","volume":"43","author":"Griffiths David","year":"2022","journal-title":"Computer Graphics Forum"},{"key":"e_1_2_8_14_2","unstructured":"Higgins Irina Matthey Lo\u00efc Pal Arka et al. \u201cbeta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework\u201d.International Conference on Learning Representations.2016. url:https:\/\/api.semanticscholar.org\/CorpusID:467980264."},{"key":"e_1_2_8_15_2","unstructured":"Hertz Amir Mokady Ron Tenenbaum Jay et al. \u201cPrompt-to-prompt image editing with cross attention control\u201d. (2022) 3."},{"key":"e_1_2_8_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275084"},{"key":"e_1_2_8_16_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3272127.32750842."},{"key":"e_1_2_8_17_2","first-page":"6629","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Heusel Martin","year":"2017"},{"key":"e_1_2_8_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"e_1_2_8_18_3","unstructured":"url:https:\/\/doi.org\/10.1145\/15922.159024."},{"key":"e_1_2_8_19_2","unstructured":"Kocsis Peter Philip Julien Sunkavalli Kalyan et al. \u201cLightIt: Illumination Modeling and Control for Diffusion Models\u201d.CVPR.20243."},{"key":"e_1_2_8_20_2","unstructured":"Kocsis Peter Sitzmann Vincent andNiessner Matthias. \u201cIntrinsic Image Diffusion for Indoor Single-view Material Estimation\u201d.20243."},{"key":"e_1_2_8_21_2","unstructured":"Labs Black Forest Batifol Stephen Blattmann Andreas et al.FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space.2025. arXiv: 2506.15742 [cs.GR]. url:https:\/\/arxiv.org\/abs\/2506.157423."},{"key":"e_1_2_8_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657472"},{"key":"e_1_2_8_22_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3641519.36574723 9."},{"key":"e_1_2_8_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3731173"},{"key":"e_1_2_8_23_3","unstructured":"url:https:\/\/doi.org\/10.1145\/37311733 10."},{"key":"e_1_2_8_24_2","doi-asserted-by":"crossref","unstructured":"Liang Ruofan Gojcic Zan Ling Huan et al. \u201cDiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models\u201d.arXiv preprint arXiv:2501.18590(2025) 2 3.","DOI":"10.1109\/CVPR52734.2025.02428"},{"key":"e_1_2_8_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_2_8_25_3","unstructured":"url:https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52729.2023.021563."},{"key":"e_1_2_8_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323020"},{"key":"e_1_2_8_26_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3306346.33230202."},{"key":"e_1_2_8_27_2","doi-asserted-by":"crossref","unstructured":"Li Shanglin Zeng Bohan Feng Yutang et al. \u201cZONE: Zero-Shot Instruction-Guided Local Editing\u201d.2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2024 6254\u20136263. doi:10.1109\/CVPR52733.2024.005983.","DOI":"10.1109\/CVPR52733.2024.00598"},{"key":"e_1_2_8_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_2_8_28_3","unstructured":"url:https:\/\/doi.org\/10.1145\/35032502."},{"key":"e_1_2_8_29_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_2_8_29_3","unstructured":"url:https:\/\/doi.org\/10.1609\/aaai.v38i5.282262 3."},{"key":"e_1_2_8_30_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13225"},{"key":"e_1_2_8_30_3","unstructured":"eprint:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.13225."},{"key":"e_1_2_8_30_4","unstructured":"url:https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1111\/cgf.132252."},{"key":"e_1_2_8_31_2","first-page":"16784","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Nichol Alexander Quinn","year":"2022"},{"key":"e_1_2_8_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459872"},{"key":"e_1_2_8_32_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3450626.34598722."},{"key":"e_1_2_8_33_2","doi-asserted-by":"crossref","unstructured":"Pandey Karran Guerrero Paul Gadelha Matheus et al. \u201cDiffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D\u201d.Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2024 7695\u201377043 5 10.","DOI":"10.1109\/CVPR52733.2024.00735"},{"key":"e_1_2_8_34_2","doi-asserted-by":"crossref","unstructured":"Park Keunhong Sinha Utkarsh Barron Jonathan T. et al. \u201cNerfies: Deformable Neural Radiance Fields\u201d.ICCV(2021) 2.","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"e_1_2_8_35_2","unstructured":"Peebles WilliamandXie Saining. \u201cScalable Diffusion Models with Transformers\u201d.arXiv preprint arXiv:2212.09748(2022) 4."},{"key":"e_1_2_8_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130855"},{"key":"e_1_2_8_36_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3130800.31308552."},{"key":"e_1_2_8_37_2","first-page":"1060","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48","author":"Reed Scott","year":"2016"},{"key":"e_1_2_8_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_2_8_38_3","unstructured":"url:https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52688.2022.010421 2."},{"key":"e_1_2_8_39_2","unstructured":"Rudnev Viktor Elgharib Mohamed Smith William et al. \u201cNeRF for Outdoor Scene Relighting\u201d.European Conference on Computer Vision (ECCV).20223."},{"key":"e_1_2_8_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_2_8_40_3","unstructured":"url:https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52729.2023.021553."},{"key":"e_1_2_8_41_2","first-page":"8821","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Ramesh Aditya","year":"2021"},{"key":"e_1_2_8_42_2","doi-asserted-by":"crossref","unstructured":"Roberts Mike Ramapuram Jason Ranjan Anurag et al. \u201cHypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding\u201d.International Conference on Computer Vision (ICCV) 2021.20215.","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"e_1_2_8_43_2","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Saharia Chitwan","year":"2022"},{"key":"e_1_2_8_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/97879.97901"},{"key":"e_1_2_8_44_3","unstructured":"url:https:\/\/doi.org\/10.1145\/97879.979012."},{"key":"e_1_2_8_45_2","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/978-3-030-58517-4_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Tretschk Edgar","year":"2020"},{"key":"e_1_2_8_46_2","unstructured":"Wu Chenfei Li Jiahao Zhou Jingren et al.Qwen-Image Technical Report.2025. arXiv: 2508.02324 [cs.CV]. url:https:\/\/arxiv.org\/abs\/2508.023243."},{"key":"e_1_2_8_47_2","unstructured":"Wang Zian Shen Tianchang Gao Jun et al. \u201cNeural Fields meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes\u201d.The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June20233."},{"key":"e_1_2_8_48_2","volume-title":"Eurographics Symposium on Rendering","author":"Xue Bowen","year":"2024"},{"key":"e_1_2_8_49_2","doi-asserted-by":"crossref","unstructured":"Xu Tao Zhang Pengchuan Huang Qiuyuan et al. \u201cAttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks\u201d.2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2018 1316\u20131324. doi:10.1109\/CVPR.2018.001432.","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_2_8_50_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15116"},{"key":"e_1_2_8_50_3","unstructured":"eprint:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.15116."},{"key":"e_1_2_8_50_4","unstructured":"url:https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1111\/cgf.151162."},{"key":"e_1_2_8_51_2","unstructured":"Yu Ye Meka Abhimetra Elgharib Mohamed et al. \u201cSelf-supervised Outdoor Scene Relighting\u201d.European Conference on Computer Vision (ECCV).20202."},{"key":"e_1_2_8_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657445"},{"key":"e_1_2_8_52_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3641519.36574452 6 8 9."},{"key":"e_1_2_8_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657396"},{"key":"e_1_2_8_53_3","unstructured":"url:http:\/\/dx.doi.org\/10.1145\/3641519.36573963."},{"key":"e_1_2_8_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555407"},{"key":"e_1_2_8_54_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3550469.35554072."},{"key":"e_1_2_8_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555407"},{"key":"e_1_2_8_55_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3550469.35554075."},{"key":"e_1_2_8_56_2","unstructured":"Zhang Lvmin Rao Anyi andAgrawala Maneesh.Adding Conditional Control to Text-to-Image Diffusion Models.20232 3."},{"key":"e_1_2_8_57_2","doi-asserted-by":"crossref","unstructured":"Zhang Han Xu Tao Li Hongsheng et al. \u201cStackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks\u201d.2017 IEEE International Conference on Computer Vision (ICCV).2017 5908\u20135916. doi:10.1109\/ICCV.2017.6292.","DOI":"10.1109\/ICCV.2017.629"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70329","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70329","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T13:10:43Z","timestamp":1775826643000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70329"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,10]]},"references-count":79,"alternative-id":["10.1111\/cgf.70329"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70329","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,10]]},"assertion":[{"value":"2026-04-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70329"}}