{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T21:09:41Z","timestamp":1789160981812,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375520","type":"print"},{"value":"9783032375537","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\/978-3-032-37553-7_29","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:57:33Z","timestamp":1789160253000},"page":"521-538","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OmniFace: Bridging the\u00a0Image-to-Video Gap for\u00a0High-Fidelity Face Swapping via\u00a0Diffusion Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7449-9450","authenticated-orcid":false,"given":"Xu","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fulong","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinghui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengqi","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengze","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qichao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songtao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangwang","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Baliah, S., Lin, Q., Liao, S., Liang, X., Khan, M.H.: Realistic and efficient face swapping: a unified approach with diffusion models. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1062\u20131071. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00112"},{"key":"29_CR2","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets (2023). arXiv preprint arXiv:2311.15127"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, X., Ni, B., Ge, Y.: SimSwap: an efficient framework for high fidelity face swapping. In: MM \u201920: The 28th ACM International Conference on Multimedia (2020)","DOI":"10.1145\/3394171.3413630"},{"key":"29_CR4","unstructured":"Chen, X., et al.: HiFiVFS: high fidelity video face swapping (2024). arXiv preprint arXiv:2411.18293"},{"key":"29_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, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"29_CR6","doi-asserted-by":"publisher","first-page":"53945","DOI":"10.52202\/079017-1708","volume":"37","author":"S Ding","year":"2024","unstructured":"Ding, S.: Diffusion-based reinforcement learning via q-weighted variational policy optimization. Adv. Neural. Inf. Process. Syst. 37, 53945\u201353968 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR7","unstructured":"Gao, Y., et\u00a0al.: Seedance 1.0: exploring the boundaries of video generation models. arXiv preprint arXiv:2506.09113 (2025)"},{"key":"29_CR8","unstructured":"Google: Gemini 2.5 flash image (2025). https:\/\/aistudio.google.com\/models\/gemini-2-5-flash-image. Accessed 29 Jun 2026"},{"key":"29_CR9","unstructured":"Guo, Y., et al.: AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Han, Y., et al.: Face-adapter for pre-trained diffusion models with fine-grained id and attribute control. In: European Conference on Computer Vision, pp. 20\u201336. Springer (2024)","DOI":"10.1007\/978-3-031-72973-7_2"},{"key":"29_CR11","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR12","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv:2207.12598 (2022)"},{"key":"29_CR13","doi-asserted-by":"publisher","first-page":"8633","DOI":"10.52202\/068431-0628","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., et al.: Video diffusion models. Adv. Neural. Inf. Process. Syst. 35, 8633\u20138646 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Hong, F.T., Zhang, L., Shen, L., Xu, D.: Depth-aware generative adversarial network for talking head video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3397\u20133406 (2022)","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Curricularface: adaptive curriculum learning loss for deep face recognition. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5901\u20135910 (2020)","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: Vbench: Comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"29_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111451","volume":"163","author":"K Kim","year":"2025","unstructured":"Kim, K., et al.: Diffface: Diffusion-based face swapping with facial guidance. Pattern Recogn. 163, 111451 (2025)","journal-title":"Pattern Recogn."},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Kligvasser, I., Cohen, R., Leifman, G., Rivlin, E., Elad, M.: Anchored diffusion for video face reenactment. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 4087\u20134097. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00402"},{"key":"29_CR20","unstructured":"Kong, W., et\u00a0al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: Maskgan: towards diverse and interactive facial image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5549\u20135558 (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Li, L., Bao, J., Yang, H., Chen, D., Wen, F.: Advancing high fidelity identity swapping for forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5074\u20135083 (2020)","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"29_CR23","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":"29_CR24","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Flow-GRPO: training flow matching models via online RL. arXiv preprint arXiv:2505.05470 (2025)","DOI":"10.52202\/085713-1362"},{"key":"29_CR25","unstructured":"Liu, Y., et\u00a0al.: SORA: a review on background, technology, limitations, and opportunities of large vision models. arXiv preprint arXiv:2402.17177 (2024)"},{"issue":"9","key":"29_CR26","first-page":"7449","volume":"40","author":"Z Liu","year":"2026","unstructured":"Liu, Z., Lu, J., Lu, R., Liang, C., Wang, S.: Consisttalk: intensity controllable temporally consistent talking head generation with diffusion noise search. Proc. AAAI Conf. Artif. Intell. 40(9), 7449\u20137457 (2026)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Luo, X., et al.: Canonswap: high-fidelity and consistent video face swapping via canonical space modulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10064\u201310074 (2025)","DOI":"10.1109\/ICCV51701.2025.00938"},{"key":"29_CR28","unstructured":"Ma, G., et\u00a0al.: Step-video-t2v technical report: the practice, challenges, and future of video foundation model. arXiv preprint arXiv:2502.10248 (2025)"},{"key":"29_CR29","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"},{"issue":"1","key":"29_CR30","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1109\/TPAMI.2022.3155571","volume":"45","author":"Y Nirkin","year":"2023","unstructured":"Nirkin, Y., Keller, Y., Hassner, T.: FSGANV 2: improved subject agnostic face swapping and reenactment. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 560\u2013575 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR31","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":"29_CR32","unstructured":"Ravi, N., et al.: Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"29_CR33","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"29_CR34","unstructured":"Shao, H., et al.: VividFace: a diffusion-based hybrid framework for high-fidelity video face swapping. arXiv:2412.11279 arXiv preprint (2024)"},{"key":"29_CR35","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"29_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., et al.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"29_CR37","unstructured":"The InsightFace Team: Insightface products. https:\/\/github.com\/deepinsight\/insightface. Accessed 29 June 2026"},{"key":"29_CR38","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: DynamicFace: high-quality and consistent face swapping for image and video using composable 3D facial priors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13438\u201313447 (2025)","DOI":"10.1109\/ICCV51701.2025.01248"},{"key":"29_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: HifiFace: 3D shape and semantic prior guided high fidelity face swapping. arXiv preprint arXiv:2106.09965 (2021)","DOI":"10.24963\/ijcai.2021\/157"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhu, X., Zhang, T., Wang, B., Lei, Z.: 3D face reconstruction with the geometric guidance of facial part segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1672\u20131682 (2024)","DOI":"10.1109\/CVPR52733.2024.00165"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. arXiv preprint arXiv:1611.05431 (2016)","DOI":"10.1109\/CVPR.2017.634"},{"key":"29_CR43","unstructured":"Xue, B., et al.: Stand-in: a lightweight and plug-and-play identity control for video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23314\u201323324 (2026)"},{"key":"29_CR44","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Ye, F., et al.: Dreamid: high-fidelity and fast diffusion-based face swapping via triplet id group learning. arXiv preprin arXiv:2504.14509 (2025)","DOI":"10.1145\/3757377.3763963"},{"key":"29_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, W., et al.: Diffswap: high-fidelity and controllable face swapping via 3D-aware masked diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8568\u20138577 (2023)","DOI":"10.1109\/CVPR52729.2023.00828"},{"key":"29_CR47","doi-asserted-by":"crossref","unstructured":"Zi, B., et al.: Minimax-remover: Taming bad noise helps video object removal. arXiv preprint arXiv:2505.24873 (2025)","DOI":"10.52202\/085713-2536"}],"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\/978-3-032-37553-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:57:47Z","timestamp":1789160267000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37553-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375520","9783032375537"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37553-7_29","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":"12 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"}}]}}