{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T21:16:52Z","timestamp":1764969412454,"version":"3.46.0"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"name":"Len Blavatnik and the Blavatnik family foundation","award":["1337\/22"],"award-info":[{"award-number":["1337\/22"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:p>\n                    Light control in generated images is a difficult task, posing specific challenges, spanning over the entire image and frequency spectrum. Most approaches tackle this problem by training on extensive yet domain-specific datasets, limiting the inherent generalization and applicability of the foundational backbones used. Instead,\n                    <jats:italic toggle=\"yes\">PractiLight<\/jats:italic>\n                    is a practical approach, effectively leveraging foundational understanding of recent generative models for the task. Our key insight is that lighting relationships in an image are similar in nature to token interaction in self-attention layers, and hence are best represented there. Based on this and other analyses regarding the importance of early diffusion iterations,\n                    <jats:italic toggle=\"yes\">PractiLight<\/jats:italic>\n                    trains a lightweight LoRA regressor to produce the direct-irradiance map for a given image, using a small set of training images. We then employ this regressor to incorporate the desired lighting into the generation process of another image using Classifier Guidance. This careful design generalizes well to diverse conditions and image domains. We demonstrate state-of-the-art performance in terms of quality and control with proven parameter and data efficiency compared to leading works over a wide variety of scene types. We hope this work affirms that image lighting can feasibly be controlled by tapping into foundational knowledge, enabling practical and general relighting.\n                  <\/jats:p>","DOI":"10.1145\/3763342","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T17:15:39Z","timestamp":1764868539000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PractiLight: Practical Light Control Using Foundational Diffusion Models"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8319-5111","authenticated-orcid":false,"given":"Yotam","family":"Erel","sequence":"first","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1245-4146","authenticated-orcid":false,"given":"Rishabh","family":"Dabral","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1630-2006","authenticated-orcid":false,"given":"Vladislav","family":"Golyanik","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3592-1112","authenticated-orcid":false,"given":"Amit","family":"H. Bermano","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6104-6625","authenticated-orcid":false,"given":"Christian","family":"Theobalt","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"e_1_2_2_2_1","unstructured":"Shariq Farooq Bhat Reiner Birkl Diana Wofk Peter Wonka and Matthias M\u00fcller. 2023. ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth. arXiv:2302.12288 [cs.CV] https:\/\/arxiv.org\/abs\/2302.12288"},{"key":"e_1_2_2_3_1","article-title":"Intrinsic Image Decomposition via Ordinal Shading","volume":"43","author":"Careaga Chris","year":"2023","unstructured":"Chris Careaga and Ya\u011f\u0131z Aksoy. 2023. Intrinsic Image Decomposition via Ordinal Shading. ACM Trans. Graph. 43, 1, Article 12 (2023), 24 pages.","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687984"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00537"},{"volume-title":"Blender - a 3D modelling and rendering package","author":"Community Blender Online","key":"e_1_2_2_7_1","unstructured":"Blender Online Community. 2018. Blender - a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam. http:\/\/www.blender.org"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344855"},{"key":"e_1_2_2_9_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34 (2021), 8780\u20138794."},{"key":"e_1_2_2_10_1","unstructured":"Discus0434. 2025. Aesthetic Predictor v2.5. https:\/\/github.com\/discus0434\/aesthetic-predictor-v2-5. Accessed: 2025-01-14."},{"key":"e_1_2_2_11_1","volume-title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out! arXiv:2311.17137 [cs.CV] https:\/\/arxiv.org\/abs\/2311.17137","author":"Du Xiaodan","year":"2024","unstructured":"Xiaodan Du, Nicholas Kolkin, Greg Shakhnarovich, and Anand Bhattad. 2024. Generative Models: What Do They Know? Do They Know Things? Let's Find Out! arXiv:2311.17137 [cs.CV] https:\/\/arxiv.org\/abs\/2311.17137"},{"key":"e_1_2_2_12_1","first-page":"50742","article-title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","volume":"36","author":"Fu Stephanie","year":"2023","unstructured":"Stephanie Fu, Netanel Tamir, Shobhita Sundaram, Lucy Chai, Richard Zhang, Tali Dekel, and Phillip Isola. 2023. DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data. In Advances in Neural Information Processing Systems, Vol. 36. 50742\u201350768.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00813"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_10"},{"volume-title":"Computer Graphics Forum","author":"Griffiths David","key":"e_1_2_2_15_1","unstructured":"David Griffiths, Tobias Ritschel, and Julien Philip. 2022. OutCast: Outdoor Single-image Relighting with Cast Shadows. In Computer Graphics Forum, Vol. 41. Wiley Online Library, 179\u2013193."},{"key":"e_1_2_2_16_1","volume-title":"Prompt-to-Prompt Image Editing with Cross-Attention Control. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=_CDixzkzeyb","author":"Hertz Amir","year":"2023","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohenor. 2023. Prompt-to-Prompt Image Editing with Cross-Attention Control. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=_CDixzkzeyb"},{"key":"e_1_2_2_17_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_2_2_18_1","first-page":"141129","article-title":"Neural gaffer: Relighting any object via diffusion","volume":"37","author":"Jin Haian","year":"2024","unstructured":"Haian Jin, Yuan Li, Fujun Luan, Yuanbo Xiangli, Sai Bi, Kai Zhang, Zexiang Xu, Jin Sun, and Noah Snavely. 2024. Neural gaffer: Relighting any object via diffusion. Advances in Neural Information Processing Systems 37 (2024), 141129\u2013141152.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02371"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00894"},{"key":"e_1_2_2_21_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_2_2_22_1","unstructured":"Likun Li Haoqi Zeng Changpeng Yang Haozhe Jia and Di Xu. 2024. Block-wise LoRA: Revisiting Fine-grained LoRA for Effective Personalization and Stylization in Text-to-Image Generation. arXiv:2403.07500 [cs.CV] https:\/\/arxiv.org\/abs\/2403.07500"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"e_1_2_2_24_1","volume-title":"Proceedings, Part IV 16","author":"Liu Andrew","year":"2020","unstructured":"Andrew Liu, Shiry Ginosar, Tinghui Zhou, Alexei A Efros, and Noah Snavely. 2020. Learning to factorize and relight a city. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IV 16. Springer, 544\u2013561."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00615"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00785"},{"key":"e_1_2_2_27_1","volume-title":"Aleksander Holynski, and Trevor Darrell.","author":"Luo Grace","year":"2024","unstructured":"Grace Luo, Lisa Dunlap, Dong Huk Park, Aleksander Holynski, and Trevor Darrell. 2024b. Diffusion hyperfeatures: Searching through time and space for semantic correspondence. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730696"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02070"},{"key":"e_1_2_2_30_1","volume-title":"International conference on machine learning. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/38.946629"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"e_1_2_2_35_1","volume-title":"Denoising Diffusion Implicit Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=St1giarCHLP","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"e_1_2_2_37_1","volume-title":"Microfacet Models for Refraction through Rough Surfaces. Rendering techniques 2007","author":"Walter Bruce","year":"2007","unstructured":"Bruce Walter, Stephen R Marschner, Hongsong Li, and Kenneth E Torrance. 2007. Microfacet Models for Refraction through Rough Surfaces. Rendering techniques 2007 (2007), 18th."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"e_1_2_2_39_1","unstructured":"Xiaoshi Wu Yiming Hao Keqiang Sun Yixiong Chen Feng Zhu Rui Zhao and Hongsheng Li. 2023. Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis. arXiv:2306.09341 [cs.CV] https:\/\/arxiv.org\/abs\/2306.09341"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00050"},{"key":"e_1_2_2_41_1","volume-title":"Jan Hendrik Metzen, Konrad Groh, Sezer Karaoglu, and Theo Gevers.","author":"Xing Xiaoyan","year":"2024","unstructured":"Xiaoyan Xing, Vincent Tao Hu, Jan Hendrik Metzen, Konrad Groh, Sezer Karaoglu, and Theo Gevers. 2024. Retinex-Diffusion: On Controlling Illumination Conditions in Diffusion Models via Retinex Theory. arXiv:2407.20785 [cs.CV] https:\/\/arxiv.org\/abs\/2407.20785"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657396"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657445"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_2_2_45_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Zhang Lvmin","year":"2025","unstructured":"Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. 2025. Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_2_2_46_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei A Efros Eli Shechtman and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In CVPR.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_2_47_1","first-page":"96775","article-title":"Latent intrinsics emerge from training to relight","volume":"37","author":"Zhang Xiao","year":"2024","unstructured":"Xiao Zhang, William Gao, Seemandhar Jain, Michael Maire, David Forsyth, and Anand Bhattad. 2024. Latent intrinsics emerge from training to relight. Advances in Neural Information Processing Systems 37 (2024), 96775\u201396796.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00729"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3763342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T21:13:32Z","timestamp":1764969212000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3763342"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1145\/3763342"],"URL":"https:\/\/doi.org\/10.1145\/3763342","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"type":"print","value":"0730-0301"},{"type":"electronic","value":"1557-7368"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"2025-05-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}