{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T02:48:28Z","timestamp":1769741308060,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556953","type":"print"},{"value":"9789819556960","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5696-0_12","type":"book-chapter","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T14:03:31Z","timestamp":1769695411000},"page":"166-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion Transformer-Based Lighting Control and\u00a0Identity-Preserving Personalization for\u00a0Single-Person Portraits"],"prefix":"10.1007","author":[{"given":"Danyi","family":"Chen","sequence":"first","affiliation":[]},{"given":"Siyuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Changqing","family":"Yin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"12_CR1","unstructured":"Black forest labs: Flux.1 (2024). https:\/\/flux1ai.com"},{"key":"12_CR2","unstructured":"Fancy feast: Joycaption2 (2024). joy-caption-alpha-two"},{"key":"12_CR3","unstructured":"Chadebec, C., Tasar, O., Sreetharan, S., Aubin, B.: Lbm: Latent bridge matching for fast image-to-image translation. arXiv preprint arXiv:2503.07535 (2025)"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Ding, Z., Zhang, X., Xia, Z., Jebe, L., Tu, Z., Zhang, X.: Diffusionrig: learning personalized priors for facial appearance editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12736\u201312746 (2023)","DOI":"10.1109\/CVPR52729.2023.01225"},{"key":"12_CR5","unstructured":"Esser, P., et\u00a0al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"12_CR6","first-page":"36777","volume":"37","author":"Z Guo","year":"2024","unstructured":"Guo, Z., Wu, Y., Zhuowei, C., Zhang, P., He, Q., et al.: Pulid: pure and lightning id customization via contrastive alignment. Adv. Neural. Inf. Process. Syst. 37, 36777\u201336804 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR7","unstructured":"He, J., Geng, Y., Bo, L.: Uniportrait: a unified framework for identity-preserving single-and multi-human image personalization. arXiv preprint arXiv:2408.05939 (2024)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Hou, A., Sarkis, M., Bi, N., Tong, Y., Liu, X.: Face relighting with geometrically consistent shadows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4217\u20134226 (2022)","DOI":"10.1109\/CVPR52688.2022.00418"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: Ssh: a self-supervised framework for image harmonization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4832\u20134841 (2021)","DOI":"10.1109\/ICCV48922.2021.00479"},{"key":"12_CR10","unstructured":"Jin, H., et al.: Neural gaffer: relighting any object via diffusion. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Kim, H., Jang, M., Yoon, W., Lee, J., Na, D., Woo, S.: Switchlight: co-design of physics-driven architecture and pre-training framework for human portrait relighting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 25096\u201325106 (2024)","DOI":"10.1109\/CVPR52733.2024.02371"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Li, Z., Cao, M., Wang, X., Qi, Z., Cheng, M.M., Shan, Y.: Photomaker: customizing realistic human photos via stacked id embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8640\u20138650 (2024)","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"12_CR13","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Marnerides, D., Bashford-Rogers, T., Hatchett, J., Debattista, K.: Expandnet: a deep convolutional neural network for high dynamic range expansion from low dynamic range content. In: Computer Graphics Forum, vol.\u00a037, pp. 37\u201349. Wiley Online Library (2018)","DOI":"10.1111\/cgf.13340"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Mei, Y., et al.: Lightpainter: interactive portrait relighting with freehand scribble. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 195\u2013205 (2023)","DOI":"10.1109\/CVPR52729.2023.00027"},{"issue":"4","key":"12_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459872","volume":"40","author":"R Pandey","year":"2021","unstructured":"Pandey, R., et al.: Total relighting: learning to relight portraits for background replacement. ACM Trans. Graph. 40(4), 1\u201343 (2021)","journal-title":"ACM Trans. Graph."},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Ponglertnapakorn, P., Tritrong, N., Suwajanakorn, S.: Difareli: diffusion face relighting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22646\u201322657 (2023)","DOI":"10.1109\/ICCV51070.2023.02070"},{"key":"12_CR19","unstructured":"Qin, C., et\u00a0al.: Unicontrol: A unified diffusion model for controllable visual generation in the wild. arXiv preprint arXiv:2305.11147 (2023)"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Ren, M., et al.: Relightful harmonization: lighting-aware portrait background replacement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6452\u20136462 (2024)","DOI":"10.1109\/CVPR52733.2024.00617"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR22","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"12_CR24","unstructured":"Schuhmann, C.: Laion-aesthetics (2022). https:\/\/laion.ai\/blog\/laion-aesthetics"},{"key":"12_CR25","unstructured":"Tan, Z., Liu, S., Yang, X., Xue, Q., Wang, X.: Ominicontrol: minimal and universal control for diffusion transformer. arXiv preprint arXiv:2411.15098 (2024)"},{"key":"12_CR26","unstructured":"Wang, Q., et al.: Instantid: zero-shot identity-preserving generation in seconds. arXiv preprint arXiv: 2401.07519 (2024)"},{"key":"12_CR27","unstructured":"Wei, Z., Su, Q., Qin, L., Wang, W.: Mm-diff: high-fidelity image personalization via multi-modal condition integration. arXiv preprint arXiv:2403.15059 (2024)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Xiao, G., Yin, T., Freeman, W.T., Durand, F., Han, S.: Fastcomposer: tuning-free multi-subject image generation with localized attention. Inter. J. Comput. Vis., 1\u201320 (2024)","DOI":"10.1007\/s11263-024-02227-z"},{"key":"12_CR29","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Zeng, C., Dong, Y., Peers, P., Kong, Y., Wu, H., Tong, X.: Dilightnet: fine-grained lighting control for diffusion-based image generation. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201312 (2024)","DOI":"10.1145\/3641519.3657396"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision., pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"12_CR32","unstructured":"Zhang, L., Rao, A., Agrawala, M.: 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 (2025)"},{"key":"12_CR33","first-page":"11127","volume":"36","author":"S Zhao","year":"2023","unstructured":"Zhao, S., et al.: Uni-controlnet: all-in-one control to text-to-image diffusion models. Adv. Neural. Inf. Process. Syst. 36, 11127\u201311150 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR34","unstructured":"Zhou, Z., Li, J., Li, H., Chen, N., Tang, X.: Storymaker: Towards holistic consistent characters in text-to-image generation. arXiv preprint arXiv:2409.12576 (2024)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5696-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T14:03:47Z","timestamp":1769695427000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5696-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556953","9789819556960"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5696-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"30 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}