{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:11:18Z","timestamp":1788851478800,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370945","type":"print"},{"value":"9783032370952","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\/978-3-032-37095-2_35","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:03:57Z","timestamp":1788851037000},"page":"646-662","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Swap the Right Identity: Spatio-Temporal Diffusion Preference Optimization for Character Swapping"],"prefix":"10.1007","author":[{"given":"Hongdeng","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jikang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiongzheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunlong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"35_CR1","unstructured":"Black, K., Janner, M., Du, Y., Kostrikov, I., Levine, S.: Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301 (2023)"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, X., Ni, B., Ge, Y.: SimSwap: an efficient framework for high fidelity face swapping. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2003\u20132011 (2020)","DOI":"10.1145\/3394171.3413630"},{"issue":"1","key":"35_CR4","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1109\/TPAMI.2023.3307156","volume":"46","author":"X Chen","year":"2023","unstructured":"Chen, X., Ni, B., Liu, Y., Liu, N., Zeng, Z., Wang, H.: SimSwap++: towards faster and high-quality identity swapping. IEEE Trans. Pattern Anal. Mach. Intell. 46(1), 576\u2013592 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"35_CR6","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems (NeurIPS) (2017). arXiv:1706.08500"},{"key":"35_CR7","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"35_CR8","doi-asserted-by":"publisher","DOI":"10.1049\/el:20080522","author":"Q Huynh-Thu","year":"2008","unstructured":"Huynh-Thu, Q., Ghanbari, M.: Scope of validity of PSNR in image\/video quality assessment. Electron. Lett. (2008). https:\/\/doi.org\/10.1049\/el:20080522","journal-title":"Electron. Lett."},{"key":"35_CR9","unstructured":"Labs, B.F.: FLUX.2: frontier visual intelligence (2025). https:\/\/bfl.ai\/blog\/flux-2"},{"key":"35_CR10","unstructured":"Li, L., Bao, J., Yang, H., Chen, D., Wen, F.: FaceShifter: towards high fidelity and occlusion aware face swapping. arXiv preprint arXiv:1912.13457 (2019)"},{"key":"35_CR11","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 (CVPR), pp. 8640\u20138650 (2024)","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"35_CR12","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"35_CR13","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2I-Adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Nirkin, Y., Keller, Y., Hassner, T.: FSGAN: subject agnostic face swapping and reenactment. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7184\u20137193 (2019)","DOI":"10.1109\/ICCV.2019.00728"},{"key":"35_CR16","unstructured":"OpenAI: GPT image 1.5 model (2025). https:\/\/platform.openai.com\/docs\/models\/gpt-image-1.5. Accessed 28 Jan 2026. Snapshot listed: GPT-image-1.5-2025-12-16"},{"key":"35_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 (ICCV), pp. 4199\u20134209 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"35_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML) (2021). arXiv:2103.00020"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 36 (2023)","DOI":"10.52202\/075280-2338"},{"key":"35_CR20","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 (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"35_CR22","unstructured":"Shao, H., et al.: VividFace: a diffusion-based hybrid framework for high-fidelity video face swapping. arXiv preprint arXiv:2412.11279 (2024)"},{"key":"35_CR23","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Wallace, B., et al.: Diffusion model alignment using direct preference optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8228\u20138238 (2024)","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"35_CR25","unstructured":"Wang, Q., Bai, X., Wang, H., Qin, Z., Chen, A.: Instantid: zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:2401.07519 (2024)"},{"key":"35_CR26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. (2004). https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans. Image Process."},{"key":"35_CR27","unstructured":"Wu, C., et al.: Qwen-image technical report. arXiv:2508.02324 (2025)"},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Yang, K., et al.: Using human feedback to fine-tune diffusion models without any reward model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8941\u20138951 (2024)","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"35_CR29","unstructured":"Yang, X., Cheng, C., Yang, X., Liu, F., Lin, G.: Text-to-image rectified flow as plug-and-play priors. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=SzPZK856iI"},{"key":"35_CR30","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":"35_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 (ICCV), pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Shi, W., Liu, Z., Zhou, J., Lu, J.: DIFFSwap: high-fidelity and controllable face swapping via 3D-aware masked diffusion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00828"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37095-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:04:02Z","timestamp":1788851042000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37095-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370945","9783032370952"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37095-2_35","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":"9 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}