{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:55:26Z","timestamp":1777654526270,"version":"3.51.4"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732225","type":"print"},{"value":"9783031732232","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"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\/978-3-031-73223-2_2","type":"book-chapter","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T18:49:15Z","timestamp":1731005355000},"page":"18-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["InstructGIE: Towards Generalizable Image Editing"],"prefix":"10.1007","author":[{"given":"Zichong","family":"Meng","sequence":"first","affiliation":[]},{"given":"Changdi","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Pu","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"2_CR1","first-page":"25005","volume":"35","author":"A Bar","year":"2022","unstructured":"Bar, A., Gandelsman, Y., Darrell, T., Globerson, A., Efros, A.: Visual prompting via image inpainting. Adv. Neural. Inf. Process. Syst. 35, 25005\u201325017 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR2","unstructured":"Blau, T., Ganz, R., Kawar, B., Bronstein, A., Elad, M.: Threat model-agnostic adversarial defense using diffusion models. arXiv preprint arXiv:2207.08089 (2022)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"2_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR5","unstructured":"Chen, W., Hu, H., Saharia, C., Cohen, W.W.: Re-Imagen: retrieval-augmented text-to-image generator. arXiv preprint arXiv:2209.14491 (2022)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: StarGAN v2: diverse image synthesis for multiple domains. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8188\u20138197 (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"2_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: Richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"2_CR10","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. ICLR (2021)"},{"key":"2_CR12","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":"2_CR13","unstructured":"Geng, X., Liu, H.: OpenLLaMA: an open reproduction of llama (2023). https:\/\/github.com\/openlm-research\/open_llama"},{"key":"2_CR14","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"2_CR15","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"2_CR16","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":"2_CR17","unstructured":"Huang, Y., et al.: Diffusion model-based image editing: a survey. arXiv preprint arXiv:2402.17525 (2024)"},{"key":"2_CR18","unstructured":"Huang, Y., et al.: Diffusion model-based image editing: a survey. arXiv preprint arXiv:2402.17525 (2024)"},{"key":"2_CR19","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":"2_CR20","first-page":"23593","volume":"35","author":"B Kawar","year":"2022","unstructured":"Kawar, B., Elad, M., Ermon, S., Song, J.: Denoising diffusion restoration models. Adv. Neural. Inf. Process. Syst. 35, 23593\u201323606 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR21","unstructured":"Kawar, B., Ganz, R., Elad, M.: Enhancing diffusion-based image synthesis with robust classifier guidance. arXiv preprint arXiv:2208.08664 (2022)"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"2_CR23","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol.\u00a025. Curran Associates, Inc. (2012)"},{"key":"2_CR24","unstructured":"Kwon, G., Ye, J.C.: Diffusion-based image translation using disentangled style and content representation. arXiv preprint arXiv:2209.15264 (2022)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: More control for free! image synthesis with semantic diffusion guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 289\u2013299 (2023)","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"2_CR26","unstructured":"Liu, Y., et al.: VMamba: Visual state space model. arXiv preprint arXiv:2401.10166 (2024)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"2_CR28","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"2_CR29","unstructured":"Mohammad, S., Kiritchenko, S.: WikiArt emotions: an annotated dataset of emotions evoked by art. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (2018)"},{"key":"2_CR30","unstructured":"Nguyen, T., Li, Y., Ojha, U., Lee, Y.J.: Visual instruction inversion: image editing via visual prompting. arXiv preprint arXiv:2307.14331 (2023)"},{"key":"2_CR31","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR32","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"2_CR33","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"2_CR34","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"},{"key":"2_CR35","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"2_CR36","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"2_CR37","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"2_CR38","unstructured":"Sun, Y., et al.: ImageBrush: learning visual in-context instructions for exemplar-based image manipulation. arXiv preprint arXiv:2308.00906 (2023)"},{"key":"2_CR39","unstructured":"Theis, L., Salimans, T., Hoffman, M.D., Mentzer, F.: Lossy compression with gaussian diffusion. arXiv preprint arXiv:2206.08889 (2022)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, W., Cao, Y., Shen, C., Huang, T.: Images speak in images: a generalist painter for in-context visual learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6830\u20136839 (2023)","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"2_CR41","unstructured":"Wang, Z., et\u00a0al.: In-context learning unlocked for diffusion models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"2_CR42","unstructured":"Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)"},{"key":"2_CR43","unstructured":"Zablotskaia, P., Siarohin, A., Zhao, B., Sigal, L.: DwNet: dense warp-based network for pose-guided human video generation. arXiv preprint arXiv:1910.09139 (2019)"},{"key":"2_CR44","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":"2_CR45","unstructured":"Zimmermann, R.S., Schott, L., Song, Y., Dunn, B.A., Klindt, D.A.: Score-based generative classifiers. arXiv preprint arXiv:2110.00473 (2021)"}],"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\/978-3-031-73223-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:03:01Z","timestamp":1731006181000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73223-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,8]]},"ISBN":["9783031732225","9783031732232"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73223-2_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,8]]},"assertion":[{"value":"8 November 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"}}]}}