{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T21:08:48Z","timestamp":1790716128729,"version":"4.1.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250620","type":"print"},{"value":"9783031250637","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25063-7_15","type":"book-chapter","created":{"date-parts":[[2023,2,15]],"date-time":"2023-02-15T20:10:15Z","timestamp":1676491815000},"page":"239-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Unifying Conditional and\u00a0Unconditional Semantic Image Synthesis with\u00a0OCO-GAN"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4542-5371","authenticated-orcid":false,"given":"Marl\u00e8ne","family":"Careil","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6927-8930","authenticated-orcid":false,"given":"St\u00e9phane","family":"Lathuili\u00e8re","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Camille","family":"Couprie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1419-1816","authenticated-orcid":false,"given":"Jakob","family":"Verbeek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,16]]},"reference":[{"key":"15_CR1","unstructured":"Azadi, S., Tschannen, M., Tzeng, E., Gelly, S., Darrell, T., Lucic, M.: Semantic bottleneck scene generation. arXiv preprint arXiv:1911.11357 (2019)"},{"key":"15_CR2","unstructured":"Bau, D., et al.: GAN dissection: visualizing and understanding generative adversarial networks. In: ICLR (2019)"},{"key":"15_CR3","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2019)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: COCO-Stuff: thing and stuff classes in context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"15_CR5","unstructured":"Casanova, A., Careil, M., Verbeek, J., Drozdzal, M., Romero-Soriano, A.: Instance-conditioned GAN. In: NeurIPS (2021)"},{"key":"15_CR6","unstructured":"Chen, L., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. In: CVPR (2017)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: CVPR (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The Cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"15_CR9","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"15_CR10","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: NeurIPS (2017)"},{"key":"15_CR11","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Huang, X., Mallya, A., Wang, T.C., Liu, M.Y.: Multimodal conditional image synthesis with product-of-experts GANs. arXiv preprint arXiv:2112.05130 (2021)","DOI":"10.1007\/978-3-031-19787-1_6"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"15_CR14","unstructured":"Jacob Walker, Ali Razavi, A.v.: Predicting video with VQVAE. arXiv preprint arXiv:2103.01950 (2021)"},{"key":"15_CR15","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANSs for improved quality, stability, and variation. In: ICLR (2018)"},{"key":"15_CR16","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"15_CR17","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. In: NeurIPS (2020)"},{"key":"15_CR18","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. In: NeurIPS (2021)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Kim, H., Choi, Y., Kim, J., Yoo, S., Uh, Y.: Exploiting spatial dimensions of latent in GAN for real-time image editing. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00091"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: MaskGAN: towards diverse and interactive facial image manipulation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., Lu, J., Shechtman, E., Lee, Y.J., Singh, K.K.: Collaging class-specific GANs for semantic image synthesis. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01415"},{"key":"15_CR23","unstructured":"Liu, X., Yin, G., Shao, J., Wang, X.: Learning to predict layout-to-image conditional convolutions for semantic image synthesis. In: NeurIPS (2019)"},{"key":"15_CR24","unstructured":"Lucic, M., Tschannen, M., Ritter, M., Zhai, X., Bachem, O., Gelly, S.: High-fidelity image generation with fewer labels. In: ICML (2019)"},{"key":"15_CR25","unstructured":"Mescheder, L., Nowozin, S., Geiger, A.: Which training methods for gans do actually converge? In: International Conference on Machine Learning (ICML) (2018)"},{"key":"15_CR26","unstructured":"Nash, C., Ganin, Y., Eslami, S., Battaglia, P.: PolyGen: an autoregressive generative model of 3D meshes. In: ICML (2020)"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Clune, J., Bengio, Y., Dosovitskiy, A., Yosinski, J.: Plug and play generative networks: conditional iterative generation of images in latent space. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.374"},{"key":"15_CR28","unstructured":"Noroozi, M.: Self-labeled conditional GANs. arXiv preprint arXiv:2012.02162 (2020)"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Park, J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"15_CR31","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 8821\u20138831. PMLR, 18\u201324 July 2021"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Richardson, E., et al.: Encoding in style: a StyleGAN encoder for image-to-image translation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: StyleGAN-XL: Scaling StyleGAN to large diverse datasets. arXiv preprint arXiv:2202.00273 (2022)","DOI":"10.1145\/3528233.3530738"},{"key":"15_CR35","doi-asserted-by":"publisher","unstructured":"Sun, W., Wu, T.: Learning layout and style reconfigurable GANs for controllable image synthesis. IEEE Trans. Pattern Anal. Mach. Intell. 1\u20131 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2021.3078577","DOI":"10.1109\/TPAMI.2021.3078577"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Sushko, V., Sch\u00f6nfeld, E., Zhang, D., Gall, J., Schiele, B., Khoreva, A.: You only need adversarial supervision for semantic image synthesis. In: ICLR (2021)","DOI":"10.1007\/s11263-022-01673-x"},{"key":"15_CR37","unstructured":"Sylvain, T., Zhang, P., Bengio, Y., Hjelm, R.D., Sharma, S.: Object-centric image generation from layouts. CoRR abs\/2003.07449 (2020)"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Tran, N.T., Tran, V.H., Nguyen, N.B., Nguyen, T.K., Cheung, N.M.: On data augmentation for GAN training. arXiv preprint arXiv:2006.05338 (2020)","DOI":"10.1109\/TIP.2021.3049346"},{"key":"15_CR39","unstructured":"Vahdat, A., Kautz, J.: NVAE: a deep hierarchical variational autoencoder. arXiv preprint arXiv:2007.03898 (2020)"},{"key":"15_CR40","unstructured":"Voynov, A., Babenko, A.: Unsupervised discovery of interpretable directions in the GAN latent space. In: ICML (2020)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Y., Qi, L., Chen, Y.C., Zhang, X., Jia, J.: Image synthesis via semantic composition. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01349"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Statistical parametric speech synthesis using generative adversarial networks under a multi-task learning framework. arXiv preprint arXiv:1707.01670 (2017)","DOI":"10.1109\/ASRU.2017.8269003"},{"key":"15_CR43","unstructured":"Zhao, S., Liu, Z., Lin, J., Zhu, J.Y., Han, S.: Differentiable augmentation for data-efficient GAN training. In: NeurIPS (2020)"},{"key":"15_CR44","unstructured":"Zhao, Z., Singh, S., Lee, H., Zhang, Z., Odena, A., Zhang, H.: Improved consistency regularization for GANs. arXiv preprint arXiv:2002.04724 (2020)"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"15_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1007\/978-3-030-58520-4_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Zhu","year":"2020","unstructured":"Zhu, J., Shen, Y., Zhao, D., Zhou, B.: In-domain GAN inversion for real image editing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 592\u2013608. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_35"},{"key":"15_CR47","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25063-7_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T19:04:47Z","timestamp":1710270287000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25063-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250620","9783031250637"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25063-7_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"16 February 2023","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)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}