{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:19:41Z","timestamp":1776881981787,"version":"3.51.2"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731150","type":"print"},{"value":"9783031731167","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73116-7_3","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:15:38Z","timestamp":1730301338000},"page":"38-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["WAVE: Warping DDIM Inversion Features for\u00a0Zero-Shot Text-to-Video Editing"],"prefix":"10.1007","author":[{"given":"Yutang","family":"Feng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sicheng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiang","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shumin","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angela","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"3_CR1","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. arXiv preprint arXiv:2206.02779 (2022)"},{"key":"3_CR2","unstructured":"Bao, Y., et al.: LatentWarp: consistent diffusion latents for zero-shot video-to-video translation. arXiv preprint arXiv:2311.00353 (2023)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: CVPR, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Ceylan, D., Huang, C.H.P., Mitra, N.J.: Pix2Video: video editing using image diffusion. arXiv preprint arXiv:2303.12688 (2023)","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Wang, X., Xu, X., Gu, J., Loy, C.C.: Glean: generative latent bank for large-factor image super-resolution. In: CVPR, pp. 14245\u201314254 (2021)","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"3_CR6","unstructured":"Cong, Y., et\u00a0al.: Flatten: optical flow-guided attention for consistent text-to-video editing. In: ICLR (2023)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Dong, W., Xue, S., Duan, X., Han, S.: Prompt tuning inversion for text-driven image editing using diffusion models. In: ICCV, pp. 7430\u20137440 (2023)","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Duan, X., et al.: Tuning-free inversion-enhanced control for consistent image editing. In: AAAI, vol.\u00a038, pp. 1644\u20131652 (2024)","DOI":"10.1609\/aaai.v38i2.27931"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models. arXiv preprint arXiv:2302.03011 (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Gao, S., et al.: Implicit diffusion models for continuous super-resolution. In: CVPR, pp. 10021\u201310030 (2023)","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"3_CR11","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., Dekel, T.: TokenFlow: consistent diffusion features for consistent video editing. In: ICLR (2024)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Gu, J., Shen, Y., Zhou, B.: Image processing using multi-code GAN prior. In: CVPR, pp. 3012\u20133021 (2020)","DOI":"10.1109\/CVPR42600.2020.00308"},{"issue":"2","key":"3_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3233304","volume":"1","author":"E Heitz","year":"2018","unstructured":"Heitz, E., Neyret, F.: High-performance by-example noise using a histogram-preserving blending operator. Proc. ACM Comput. Graph. Interact. Tech. 1(2), 1\u201325 (2018)","journal-title":"Proc. ACM Comput. Graph. Interact. Tech."},{"key":"3_CR14","unstructured":"Ho, J., et\u00a0al.: Imagen video: high definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"3_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS 33, 6840\u20136851 (2020)","journal-title":"NeurIPS"},{"key":"3_CR16","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv:2204.03458 (2022)"},{"issue":"4","key":"3_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3323006","volume":"38","author":"O Jamri\u0161ka","year":"2019","unstructured":"Jamri\u0161ka, O., et al.: Stylizing video by example. ACM TOG 38(4), 1\u201311 (2019)","journal-title":"ACM TOG"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2Video-Zero: text-to-image diffusion models are zero-shot video generators. In: ICCV, pp. 15954\u201315964 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: UV-IDM: identity-conditioned latent diffusion model for face UV-texture generation. In: CVPR, pp. 10585\u201310595 (2024)","DOI":"10.1109\/CVPR52733.2024.01007"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Zone: zero-shot instruction-guided local editing. In: CVPR, pp. 6254\u20136263 (2024)","DOI":"10.1109\/CVPR52733.2024.00598"},{"key":"3_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/978-3-030-58548-8_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Liang","year":"2020","unstructured":"Liang, J., Pei, W., Lu, F.: CPGAN: content-parsing generative adversarial networks for text-to-image synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 491\u2013508. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_29"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, Y., Li, W., Lin, Z., Jia, J.: Video-P2P: video editing with cross-attention control. arXiv preprint arXiv:2303.04761 (2023)","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: LadiffGAN: training GANs with diffusion supervision in latent spaces. In: CVPRW, pp. 1115\u20131125 (2024)","DOI":"10.1109\/CVPRW63382.2024.00118"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Meister, S., Hur, J., Roth, S.: Unflow: unsupervised learning of optical flow with a bidirectional census loss. In: AAAI, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12276"},{"key":"3_CR25","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. arXiv preprint arXiv:2211.09794 (2022)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"3_CR27","unstructured":"Molad, E., et al.: Dreamix: video diffusion models are general video editors. arXiv preprint arXiv:2302.01329 (2023)"},{"key":"3_CR28","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML, pp. 16784\u201316804. PMLR (2022)"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Pidhorskyi, S., Adjeroh, D.A., Doretto, G.: Adversarial latent autoencoders. In: CVPR, pp. 14104\u201314113 (2020)","DOI":"10.1109\/CVPR42600.2020.01411"},{"key":"3_CR30","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van\u00a0Gool, L.: The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Qi, C., et al.: FateZero: fusing attentions for zero-shot text-based video editing. In: ICCV, pp. 15932\u201315942 (2023)","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: MirrorGAN: learning text-to-image generation by redescription. In: CVPR, pp. 1505\u20131514 (2019)","DOI":"10.1109\/CVPR.2019.00160"},{"key":"3_CR33","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"3_CR34","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML, pp. 1060\u20131069. PMLR (2016)"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"3_CR37","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS 35, 36479\u201336494 (2022)","journal-title":"NeurIPS"},{"key":"3_CR38","unstructured":"Singer, U., et\u00a0al.: Make-a-video: text-to-video generation without text-video data. In: ICLR (2023)"},{"key":"3_CR39","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"3_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/978-3-642-15549-9_32","volume-title":"Computer Vision \u2013 ECCV 2010","author":"N Sundaram","year":"2010","unstructured":"Sundaram, N., Brox, T., Keutzer, K.: Dense point trajectories by GPU-accelerated large displacement optical flow. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 438\u2013451. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_32"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: CVPR, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"3_CR42","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)"},{"key":"3_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/978-3-030-58542-6_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Viazovetskyi","year":"2020","unstructured":"Viazovetskyi, Y., Ivashkin, V., Kashin, E.: StyleGAN2 distillation for feed-forward image manipulation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 170\u2013186. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_11"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. In: ICCV, pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"issue":"3","key":"3_CR45","first-page":"3121","volume":"45","author":"W Xia","year":"2022","unstructured":"Xia, W., Zhang, Y., Yang, Y., Xue, J.H., Zhou, B., Yang, M.H.: Gan inversion: a survey. IEEE TPAMI 45(3), 3121\u20133138 (2022)","journal-title":"IEEE TPAMI"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., Tao, D.: GMFlow: learning optical flow via global matching. In: CVPR, pp. 8121\u20138130 (2022)","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Yu, S., Sohn, K., Kim, S., Shin, J.: Video probabilistic diffusion models in projected latent space. In: CVPR, pp. 18456\u201318466 (2023)","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"3_CR48","unstructured":"Zeng, B., et al.: IPDreamer: appearance-controllable 3D object generation with image prompts. arXiv preprint arXiv:2310.05375 (2023)"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Zeng, B., et al.: Controllable mind visual diffusion model. In: AAAI, vol.\u00a038, pp. 6935\u20136943 (2024)","DOI":"10.1609\/aaai.v38i7.28519"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Zeng, B., et al.: Face animation with an attribute-guided diffusion model. In: CVPRW, pp. 628\u2013637 (2023)","DOI":"10.1109\/CVPRW59228.2023.00070"},{"key":"3_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV, pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"3_CR53","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, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"3_CR54","unstructured":"Zhao, M., Wang, R., Bao, F., Li, C., Zhu, J.: ControlVideo: adding conditional control for one shot text-to-video editing. arXiv preprint arXiv:2305.17098 (2023)"},{"key":"3_CR55","unstructured":"Zhou, D., Wang, W., Yan, H., Lv, W., Zhu, Y., Feng, J.: MagicVideo: efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018 (2022)"},{"key":"3_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/978-3-319-46454-1_36","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J-Y Zhu","year":"2016","unstructured":"Zhu, J.-Y., Kr\u00e4henb\u00fchl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 597\u2013613. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_36"},{"key":"3_CR57","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: DM-GAN: dynamic memory generative adversarial networks for text-to-image synthesis. In: CVPR, pp. 5802\u20135810 (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"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\/978-3-031-73116-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:17:54Z","timestamp":1730301474000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73116-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031731150","9783031731167"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73116-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 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"}}]}}