{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:10:58Z","timestamp":1789035058298,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371959","type":"print"},{"value":"9783032371966","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\/978-3-032-37196-6_15","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:36:13Z","timestamp":1789032973000},"page":"270-286","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EchoStyle: Unlocking High-Fidelity Video Stylization with\u00a0Reverse Data Synthesis"],"prefix":"10.1007","author":[{"given":"Huaqiu","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijia","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hualian","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"15_CR1","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"15_CR2","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"issue":"6","key":"15_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3687945","volume":"43","author":"H Chefer","year":"2024","unstructured":"Chefer, H., et al.: Still-moving: customized video generation without customized video data. ACM Trans. Graphics (TOG) 43(6), 1\u201311 (2024)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Dong, Q., et\u00a0al.: A survey on in-context learning. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 1107\u20131128 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"15_CR5","doi-asserted-by":"publisher","unstructured":"Frenkel, Y., Vinker, Y., Shamir, A., Cohen-Or, D.: Implicit style-content separation using B-LoRA. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15068, pp. 181\u2013198. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72684-2_11","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"15_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1007\/978-3-030-20876-9_40","volume-title":"Computer Vision \u2013 ACCV 2018","author":"C Gao","year":"2019","unstructured":"Gao, C., Gu, D., Zhang, F., Yu, Y.: ReCoNet: real-time coherent video style transfer network. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11366, pp. 637\u2013653. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20876-9_40"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: Styleshot: a snapshot on any style. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. IEEE (2025)","DOI":"10.1109\/TPAMI.2025.3610614"},{"key":"15_CR8","unstructured":"Gao, Y., et al.: Seedance 1.0: exploring the boundaries of video generation models. arXiv (Cornell University) (2025). https:\/\/doi.org\/10.48550\/arxiv.2506.09113"},{"key":"15_CR9","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., Dekel, T.: Tokenflow: consistent diffusion features for consistent video editing. In: International Conference on Learning Representations (2024)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lee, H., Kudlur, M., Dumoulin, V., Shlens, J.: Exploring the structure of a real-time, arbitrary neural artistic stylization network. In: British Machine Vision Conference (2017)","DOI":"10.5244\/C.31.114"},{"key":"15_CR11","unstructured":"He, X., et al.: Id-animator: zero-shot identity-preserving human video generation. arXiv preprint arXiv:2404.15275 (2024)"},{"key":"15_CR12","unstructured":"Hu, E.J., et\u00a0al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations, vol.\u00a01, p.\u00a03 (2022)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Hu, L.: Animate anyone: consistent and controllable image-to-video synthesis for character animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8153\u20138163 (2024)","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"15_CR15","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":"15_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Han, Z., Mao, C., Zhang, J., Pan, Y., Liu, Y.: VACE: all-in-one video creation and editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17191\u201317202 (2025)","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"15_CR17","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Kong, Z., et al.: Let them talk: audio-driven multi-person conversational video generation. In: Advances in Neural Information Processing Systems, vol. 38, pp. 70990\u201371013 (2026)","DOI":"10.52202\/085713-2387"},{"key":"15_CR19","unstructured":"Ku, M., Wei, C., Ren, W., Yang, H., Chen, W.: Anyv2v: a tuning-free framework for any video-to-video editing tasks. Trans. Mach. Learn. Res. (2024)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Kwon, G., Ye, J.C.: Clipstyler: image style transfer with a single text condition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18062\u201318071 (2022)","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, Y., Huang, T., Huang, H., Wang, H., Chu, X.: LD-RPS: zero-shot unified image restoration via latent diffusion recurrent posterior sampling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13684\u201313694 (2025)","DOI":"10.1109\/ICCV51701.2025.01270"},{"key":"15_CR22","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: International Conference on Learning Representations (2023)"},{"key":"15_CR23","unstructured":"Liu, G., et al.: Stylecrafter: enhancing stylized text-to-video generation with style adapter. ACM Trans. Graphics (2024)"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, Y., Li, W., Lin, Z., Jia, J.: Video-p2p: Video editing with cross-attention control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8599\u20138608 (2024)","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z.S., Wang, L.W., Siu, W.C., Kalogeiton, V.: Name your style: text-guided artistic style transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3530\u20133534 (2023)","DOI":"10.1109\/CVPRW59228.2023.00359"},{"key":"15_CR26","unstructured":"Mehraban, S., Adeli, V., Rommann, J., Taati, B., Truskovskyi, K.: Pickstyle: video-to-video style transfer with context-style adapters. arXiv preprint arXiv:2510.07546 (2025)"},{"key":"15_CR27","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":"15_CR28","doi-asserted-by":"crossref","unstructured":"Qi, T., Fang, S., Wu, Y., Xie, H., Liu, J., Chen, L., He, Q., Zhang, Y.: Deadiff: an efficient stylization diffusion model with disentangled representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8693\u20138702 (2024)","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"15_CR29","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"},{"issue":"4","key":"15_CR30","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14891","volume":"42","author":"S Shekhar","year":"2023","unstructured":"Shekhar, S., Reimann, M., Hilscher, M., Semmo, A., D\u00f6llner, J., Trapp, M.: Interactive control over temporal consistency while stylizing video streams. Comput. Graphics Forum 42(4), e14891 (2023)","journal-title":"Comput. Graphics Forum"},{"key":"15_CR31","unstructured":"Somepalli, G., et al.: Measuring style similarity in diffusion models. arXiv preprint arXiv:2404.01292 (2024)"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Song, Q., Lin, M., Zhan, W., Yan, S., Cao, L., Ji, R.: Univst: a unified framework for training-free localized video style transfer. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. IEEE (2025)","DOI":"10.1109\/TPAMI.2025.3630010"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Suresh, A.P., Jain, S., Noinongyao, P., Ganguly, A., Watchareeruetai, U., Samacoits, A.: Fastclipstyler: optimisation-free text-based image style transfer using style representations. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7316\u20137325 (2024)","DOI":"10.1109\/WACV57701.2024.00715"},{"key":"15_CR34","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"15_CR35","unstructured":"Team, K., et\u00a0al.: Kling-omni technical report. arXiv preprint arXiv:2512.16776 (2025)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Tu, S.,et al.: Stableanimator: high-quality identity-preserving human image animation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21096\u201321106 (2025)","DOI":"10.1109\/CVPR52734.2025.01965"},{"key":"15_CR37","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"15_CR38","unstructured":"Wang, H., Spinelli, M., Wang, Q., Bai, X., Qin, Z., Chen, A.: Instantstyle: free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733 (2024)"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Echoshot: multi-shot portrait video generation. In: Advances in Neural Information Processing Systems, vol. 38, pp. 22058\u201322090 (2026)","DOI":"10.52202\/085713-0745"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Motionctrl: a unified and flexible motion controller for video generation. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657518"},{"key":"15_CR41","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"15_CR42","unstructured":"Xu, J., Mei, Y., Zhang, K., Patel, V.M.: Freevis: training-free video stylization with inconsistent references. In: International Conference on Learning Representations (2026)"},{"key":"15_CR43","unstructured":"Yang, Y., et al.: Echomotion: unified human video and motion generation via dual-modality diffusion transformer. In: International Conference on Learning Representations (2026)"},{"key":"15_CR44","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":"15_CR45","unstructured":"Ye, Z., et al.: UNIC: unified in-context video editing. In: International Conference on Learning Representations (2026)"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Ye, Z., Huang, H., Wang, X., Wan, P., Zhang, D., Luo, W.: Stylemaster: stylize your video with artistic generation and translation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2630\u20132640 (2025)","DOI":"10.1109\/CVPR52734.2025.00251"},{"key":"15_CR47","unstructured":"Ye, Z., et al.: Visual-aware cot: Achieving high-fidelity visual consistency in unified models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9116\u20139126 (2026)"},{"key":"15_CR48","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":"15_CR49","unstructured":"Zhang, S., Yang, X., Zi, B., Huang, H., Zhang, C., Li, X.: Telestyle: content-preserving style transfer in images and videos. arXiv preprint arXiv:2601.20175 (2026)"},{"key":"15_CR50","unstructured":"Zhong, Z., et\u00a0al.: Anytalker: scaling multi-person talking video generation with interactivity refinement. arXiv preprint arXiv:2511.23475 (2025)"}],"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\/978-3-032-37196-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:36:33Z","timestamp":1789032993000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37196-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371959","9783032371966"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37196-6_15","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":"11 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"}}]}}