{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:17:44Z","timestamp":1775578664284,"version":"3.50.1"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197833","type":"print"},{"value":"9783031197840","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19784-0_41","type":"book-chapter","created":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T14:02:50Z","timestamp":1667138570000},"page":"707-723","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":177,"title":["Text2LIVE: Text-Driven Layered Image and\u00a0Video Editing"],"prefix":"10.1007","author":[{"given":"Omer","family":"Bar-Tal","sequence":"first","affiliation":[]},{"given":"Dolev","family":"Ofri-Amar","sequence":"additional","affiliation":[]},{"given":"Rafail","family":"Fridman","sequence":"additional","affiliation":[]},{"given":"Yoni","family":"Kasten","sequence":"additional","affiliation":[]},{"given":"Tali","family":"Dekel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,31]]},"reference":[{"key":"41_CR1","unstructured":"Disco Diffusion. https:\/\/colab.research.google.com\/github\/alembics\/disco-diffusion\/blob\/main\/Disco_Diffusion.ipynb"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"41_CR3","unstructured":"Bau, D., et al.: Paint by word. arXiv preprint arXiv:2103.10951 (2021)"},{"key":"41_CR4","volume-title":"The Art and Science of Digital Compositing: Techniques for Visual Effects, Animation and Motion Graphics","author":"R Brinkmann","year":"2008","unstructured":"Brinkmann, R.: The Art and Science of Digital Compositing: Techniques for Visual Effects, Animation and Motion Graphics. Morgan Kaufmann, Burlington (2008)"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"41_CR6","unstructured":"Crowson, K.: VQGAN+CLIP. https:\/\/colab.research.google.com\/github\/justinjohn0306\/VQGAN-CLIP\/blob\/main\/VQGAN%2BCLIP(Updated).ipynb"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Dong, H., Yu, S., Wu, C., Guo, Y.: Semantic image synthesis via adversarial learning. In: Proceedings of the IEEE International Conference on Computer Vision, ICCV (2017)","DOI":"10.1109\/ICCV.2017.608"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"41_CR9","unstructured":"Frans, K., Soros, L., Witkowski, O.: CLIPDraw: exploring text-to-drawing synthesis through language-image encoders. arXiv preprint arXiv:2106.14843 (2021)"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Gal, R., Patashnik, O., Maron, H., Chechik, G., Cohen-Or, D.: StyleGAN-NADA: CLIP-guided domain adaptation of image generators. arXiv preprint arXiv:2108.00946 (2021)","DOI":"10.1145\/3528223.3530164"},{"key":"41_CR11","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"41_CR13","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 Trans. Graph. 38, 1\u201311 (2019)","journal-title":"ACM Trans. Graph."},{"issue":"11","key":"41_CR14","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.1109\/TVCG.2019.2921336","volume":"26","author":"Y Jing","year":"2019","unstructured":"Jing, Y., Yang, Y., Feng, Z., Ye, J., Yu, Y., Song, M.: Neural style transfer: a review. IEEE Trans. Visual Comput. Graphics 26(11), 3365\u20133385 (2019)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"41_CR15","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"issue":"6","key":"41_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480546","volume":"40","author":"Y Kasten","year":"2021","unstructured":"Kasten, Y., Ofri, D., Wang, O., Dekel, T.: Layered neural atlases for consistent video editing. ACM Trans. Graph. (TOG) 40(6), 1\u201312 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR17","unstructured":"Kim, G., Ye, J.C.: DiffusionCLIP: text-guided image manipulation using diffusion models. arXiv preprint arXiv:2110.02711 (2021)"},{"key":"41_CR18","doi-asserted-by":"crossref","unstructured":"Kolkin, N.I., Salavon, J., Shakhnarovich, G.: Style transfer by relaxed optimal transport and self-similarity. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01029"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Kwon, G., Ye, J.C.: CLIPstyler: image style transfer with a single text condition. arXiv preprint arXiv:2112.00374 (2021)","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.H.: ManiGAN: text-guided image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"41_CR21","unstructured":"Lin, S., Fisher, M., Dai, A., Hanrahan, P.: LayerBuilder: layer decomposition for interactive image and video color editing. arXiv preprint arXiv:1701.03754 (2017)"},{"key":"41_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"41_CR23","unstructured":"Liu, X., Gong, C., Wu, L., Zhang, S., Su, H., Liu, Q.: FuseDream: training-free text-to-image generation with improved CLIP+GAN space optimization. arXiv preprint arXiv:2112.01573 (2021)"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Lu, E., et al.: Layered neural rendering for retiming people in video. ACM Trans. Graph. (2020)","DOI":"10.1145\/3414685.3417760"},{"key":"41_CR25","doi-asserted-by":"crossref","unstructured":"Lu, E., Cole, F., Dekel, T., Zisserman, A., Freeman, W.T., Rubinstein, M.: Omnimatte: associating objects and their effects in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00448"},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"Michel, O., Bar-On, R., Liu, R., Benaim, S., Hanocka, R.: Text2Mesh: text-driven neural stylization for meshes. arXiv preprint arXiv:2112.03221 (2021)","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"41_CR27","unstructured":"Nam, S., Kim, Y., Kim, S.J.: Text-adaptive generative adversarial networks: manipulating images with natural language. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"41_CR28","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"41_CR29","unstructured":"Park, T., et al.: Swapping autoencoder for deep image manipulation. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"41_CR30","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleCLIP: text-driven manipulation of StyleGAN imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"41_CR31","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van Gool, L.: The 2017 DAVIS challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"key":"41_CR32","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML) (2021)"},{"key":"41_CR33","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Proceedings of the 38th International Conference on Machine Learning (ICML) (2021)"},{"key":"41_CR34","doi-asserted-by":"crossref","unstructured":"Rav-Acha, A., Kohli, P., Rother, C., Fitzgibbon, A.W.: Unwrap mosaics: a new representation for video editing. ACM Trans. Graph. (2008)","DOI":"10.1145\/1399504.1360616"},{"key":"41_CR35","unstructured":"Reed, S.E., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: Proceedings of the 33rd International Conference on Machine Learning (ICML) (2016)"},{"key":"41_CR36","doi-asserted-by":"crossref","unstructured":"Richardson, E., et al.: Encoding in style: a StyleGAN encoder for image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"41_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/978-3-319-45886-1_3","volume-title":"Pattern Recognition","author":"M Ruder","year":"2016","unstructured":"Ruder, M., Dosovitskiy, A., Brox, T.: Artistic style transfer for videos. In: Rosenhahn, B., Andres, B. (eds.) GCPR 2016. LNCS, vol. 9796, pp. 26\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-45886-1_3"},{"key":"41_CR38","doi-asserted-by":"crossref","unstructured":"Shaham, T.R., 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":"41_CR39","doi-asserted-by":"crossref","unstructured":"Shechtman, E., Irani, M.: Matching local self-similarities across images and videos. In: 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (2007)","DOI":"10.1109\/CVPR.2007.383198"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Shocher, A., Bagon, S., Isola, P., Irani, M.: InGAN: capturing and retargeting the \u201cDNA\u201d of a natural image. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00459"},{"key":"41_CR41","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"41_CR42","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: 9th International Conference on Learning Representations (ICLR) (2021)"},{"issue":"4","key":"41_CR43","doi-asserted-by":"publisher","first-page":"73:1","DOI":"10.1145\/3386569.3392453","volume":"39","author":"O Texler","year":"2020","unstructured":"Texler, O., et al.: Interactive video stylization using few-shot patch-based training. ACM Trans. Graph. 39(4), 73:1 (2020)","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"41_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459838","volume":"40","author":"O Tov","year":"2021","unstructured":"Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., Cohen-Or, D.: Designing an encoder for StyleGAN image manipulation. ACM Trans. Graph. (TOG) 40(4), 1\u201314 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR45","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Bar-Tal, O., Bagon, S., Dekel, T.: Splicing ViT features for semantic appearance transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"41_CR46","doi-asserted-by":"crossref","unstructured":"Xia, W., Zhang, Y., Yang, Y., Xue, J.H., Zhou, B., Yang, M.H.: GAN inversion: a survey. arXiv preprint arXiv:2101.05278 (2021)","DOI":"10.1109\/TPAMI.2022.3181070"},{"key":"41_CR47","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"41_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.629"},{"issue":"8","key":"41_CR49","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2019","unstructured":"Zhang, H., et al.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1947\u20131962 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19784-0_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:41:14Z","timestamp":1710358874000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19784-0_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197833","9783031197840"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19784-0_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"31 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}