{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:49:10Z","timestamp":1777657750783,"version":"3.51.4"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726545","type":"print"},{"value":"9783031726552","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72655-2_7","type":"book-chapter","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T10:12:38Z","timestamp":1733393558000},"page":"111-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["MOFA-Video: Controllable Image Animation via\u00a0Generative Motion Field Adaptions in\u00a0Frozen Image-to-Video Diffusion Model"],"prefix":"10.1007","author":[{"given":"Muyao","family":"Niu","sequence":"first","affiliation":[]},{"given":"Xiaodong","family":"Cun","sequence":"additional","affiliation":[]},{"given":"Xintao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[]},{"given":"Yinqiang","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,6]]},"reference":[{"key":"7_CR1","unstructured":"Gen-2 (2023). https:\/\/runwayml.com\/ai-magic-tools\/gen-2\/"},{"key":"7_CR2","unstructured":"Genmo (2023). https:\/\/www.genmo.ai\/"},{"key":"7_CR3","unstructured":"I2vgen-xl (2023). https:\/\/modelscope.cn\/models\/damo\/Image-to-Video\/summary"},{"key":"7_CR4","unstructured":"Pika labs (2023). https:\/\/www.pika.art\/"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Bertiche, H., et al.: Blowing in the wind: CycleNet for human cinemagraphs from still images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00052"},{"key":"7_CR7","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Milbich, T., Dorkenwald, M., Ommer, B.: iPOKE: poking a still image for controlled stochastic video synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01444"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Milbich, T., Dorkenwald, M., Ommer, B.: Understanding object dynamics for interactive image-to-video synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00513"},{"key":"7_CR10","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"7_CR11","unstructured":"Chen, H., et al.: VideoCrafter1: open diffusion models for high-quality video generation (2023)"},{"key":"7_CR12","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":"7_CR13","doi-asserted-by":"crossref","unstructured":"Dorkenwald, M., Milbich, T., Blattmann, A., Rombach, R., Derpanis, K.G., Ommer, B.: Stochastic image-to-video synthesis using cINNs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00374"},{"key":"7_CR14","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 30 (2017)"},{"key":"7_CR15","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems 33, pp. 6840\u20136851 (2020)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Holynski, A., Curless, B.L., Seitz, S.M., Szeliski, R.: Animating pictures with Eulerian motion fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00575"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Karras, J., Holynski, A., Wang, T.C., Kemelmacher-Shlizerman, I.: DreamPose: fashion video synthesis with stable diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"7_CR18","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":"7_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.H.: Flow-grounded spatial-temporal video prediction from still images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 600\u2013615 (2018)","DOI":"10.1007\/978-3-030-01240-3_37"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Tucker, R., Snavely, N., Holynski, A.: Generative image dynamics. arXiv preprint arXiv:2309.07906 (2023)","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"7_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/978-3-030-58592-1_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"E Logacheva","year":"2020","unstructured":"Logacheva, E., Suvorov, R., Khomenko, O., Mashikhin, A., Lempitsky, V.: DeepLandscape: adversarial modeling of landscape videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 256\u2013272. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_16"},{"key":"7_CR23","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Mahapatra, A., Kulkarni, K.: Controllable animation of fluid elements in still images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00365"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Mahapatra, A., Siarohin, A., Lee, H.Y., Tulyakov, S., Zhu, J.Y.: Text-guided synthesis of Eulerian Cinemagraphs (2023)","DOI":"10.1145\/3618326"},{"issue":"9","key":"7_CR26","doi-asserted-by":"publisher","first-page":"2678","DOI":"10.1109\/TIP.2011.2131660","volume":"20","author":"ND Narvekar","year":"2011","unstructured":"Narvekar, N.D., Karam, L.J.: A no-reference image blur metric based on the cumulative probability of blur detection (CPBD). IEEE Trans. Image Process. 20(9), 2678\u20132683 (2011)","journal-title":"IEEE Trans. Image Process."},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Ni, H., Shi, C., Li, K., Huang, S.X., Min, M.R.: Conditional image-to-video generation with latent flow diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"7_CR28","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML). PMLR (2021)"},{"key":"7_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 (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Rott\u00a0Shaham, T., Dekel, T., Michaeli, T.: SinGAN: learning a generative model from a single natural image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00467"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Shi, X., et\u00a0al.: Motion-I2V: consistent and controllable image-to-video generation with explicit motion modeling. arXiv preprint arXiv:2401.15977 (2024)","DOI":"10.1145\/3641519.3657497"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O.J., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"7_CR33","unstructured":"Wang, F.Y., Chen, W., Song, G., Ye, H.J., Liu, Y., Li, H.: Gen-L-Video: multi-text to long video generation via temporal co-denoising. arXiv preprint arXiv:2305.18264 (2023)"},{"key":"7_CR34","unstructured":"Wang, Y., Yang, D., Bremond, F., Dantcheva, A.: Latent image animator: learning to animate images via latent space navigation. In: International Conference on Learning Representations (2022)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: MotionCtrl: a unified and flexible motion controller for video generation. arXiv preprint arXiv:2312.03641 (2023)","DOI":"10.1145\/3641519.3657518"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Weng, C.Y., Curless, B., Kemelmacher-Shlizerman, I.: Photo wake-up: 3D character animation from a single photo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00606"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Xiao, W., Liu, W., Wang, Y., Ghanem, B., Li, B.: Automatic animation of hair blowing in still portrait photos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.02099"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Xing, J., et\u00a0al.: Make-your-video: customized video generation using textual and structural guidance. arXiv preprint arXiv:2306.00943 (2023)","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Xing, J., et al.: DynamiCrafter: animating open-domain images with video diffusion priors (2023)","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Xiong, W., Luo, W., Ma, L., Liu, W., Luo, J.: Learning to generate time-lapse videos using multi-stage dynamic generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00251"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Xiong, W., Luo, W., Ma, L., Liu, W., Luo, J.: Learning to generate time-lapse videos using multi-stage dynamic generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2364\u20132373 (2018)","DOI":"10.1109\/CVPR.2018.00251"},{"issue":"11","key":"7_CR42","doi-asserted-by":"publisher","first-page":"13941","DOI":"10.1109\/TPAMI.2023.3298645","volume":"45","author":"H Xu","year":"2023","unstructured":"Xu, H., et al.: Unifying flow, stereo and depth estimation. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13941\u201313958 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zeng, A., Yuan, C., Li, Y.: Effective whole-body pose estimation with two-stages distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4210\u20134220 (2023)","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"7_CR44","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-3-031-19790-1_6","volume-title":"European Conference on Computer Vision","author":"F Yin","year":"2022","unstructured":"Yin, F., et al.: StyleHEAT: one-shot high-resolution editable talking face generation via pre-trained StyleGAN. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 85\u2013101. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_6"},{"key":"7_CR45","unstructured":"Yin, S., et al.: DragNUWA: fine-grained control in video generation by integrating text, image, and trajectory. arXiv preprint arXiv:2308.08089 (2023)"},{"key":"7_CR46","unstructured":"Yu, S., et al.: Generating videos with dynamics-aware implicit generative adversarial networks. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=Czsdv-S4-w9"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Zhan, X., Pan, X., Liu, Z., Lin, D., Loy, C.C.: Self-supervised learning via conditional motion propagation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1881\u20131889 (2019)","DOI":"10.1109\/CVPR.2019.00198"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: SadTalker: learning realistic 3D motion coefficients for stylized audio-driven single image talking face animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8652\u20138661 (2023)","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"7_CR51","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: ControlVideo: training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077 (2023)"},{"key":"7_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: TRIP: temporal residual learning with image noise prior for image-to-video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8671\u20138681 (2024)","DOI":"10.1109\/CVPR52733.2024.00828"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72655-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T11:27:58Z","timestamp":1733398078000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72655-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,6]]},"ISBN":["9783031726545","9783031726552"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72655-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,6]]},"assertion":[{"value":"6 December 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}