{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:07:27Z","timestamp":1777655247989,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197864","type":"print"},{"value":"9783031197871","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\/978-3-031-19787-1_25","type":"book-chapter","created":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T22:16:11Z","timestamp":1666304171000},"page":"440-456","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Vector Quantized Image-to-Image Translation"],"prefix":"10.1007","author":[{"given":"Yu-Jie","family":"Chen","sequence":"first","affiliation":[]},{"given":"Shin-I","family":"Cheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7715-8306","authenticated-orcid":false,"given":"Wei-Chen","family":"Chiu","sequence":"additional","affiliation":[]},{"given":"Hung-Yu","family":"Tseng","sequence":"additional","affiliation":[]},{"given":"Hsin-Ying","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,21]]},"reference":[{"key":"25_CR1","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning (ICML) (2020)"},{"key":"25_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/978-3-030-58571-6_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Cheng","year":"2020","unstructured":"Cheng, Y.-C., Lee, H.-Y., Sun, M., Yang, M.-H.: Controllable image synthesis via SegVAE. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 159\u2013174. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_10"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, Y.C., Lin, C.H., Lee, H.Y., Ren, J., Tulyakov, S., Yang, M.H.: InOut: diverse image outpainting via GAN inversion. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01114"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: StarGAN V2: diverse image synthesis for multiple domains. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., Jiao, J.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00110"},{"key":"25_CR7","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":"25_CR8","doi-asserted-by":"crossref","unstructured":"Han, L., et al.: Show me what and tell me how: video synthesis via multimodal conditioning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00360"},{"key":"25_CR9","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 (NeurIPS) (2017)"},{"key":"25_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1007\/978-3-030-58610-2_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H-P Huang","year":"2020","unstructured":"Huang, H.-P., Tseng, H.-Y., Lee, H.-Y., Huang, J.-B.: Semantic view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 592\u2013608. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_35"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"25_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01219-9_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Huang","year":"2018","unstructured":"Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179\u2013196. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_11"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"25_CR14","unstructured":"Kim, J., Kim, M., Kang, H., Lee, K.: U-GAT-IT: unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"25_CR15","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: International Conference on Learning Representations (ICLR) (2013)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"25_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-01246-5_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H-Y Lee","year":"2018","unstructured":"Lee, H.-Y., Tseng, H.-Y., Huang, J.-B., Singh, M., Yang, M.-H.: Diverse image-to-image translation via disentangled representations. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 36\u201352. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_3"},{"key":"25_CR18","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1007\/s11263-019-01284-z","volume":"128","author":"HY Lee","year":"2020","unstructured":"Lee, H.Y., et al.: DRIT++: diverse image-to-image translation via disentangled representations. Int. J. Comput. Vis. (IJCV) 128, 2402\u20132417 (2020)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"25_CR19","unstructured":"Lin, C.H., Lee, H.Y., Cheng, Y.C., Tulyakov, S., Yang, M.H.: InfinityGAN: towards infinite-pixel image synthesis. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"25_CR20","unstructured":"Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Mao, Q., Lee, H.Y., Tseng, H.Y., Ma, S., Yang, M.H.: Mode seeking generative adversarial networks for diverse image synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00152"},{"key":"25_CR22","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1007\/s11263-021-01557-6","volume":"130","author":"Q Mao","year":"2022","unstructured":"Mao, Q., Tseng, H.Y., Lee, H.Y., Huang, J.B., Ma, S., Yang, M.H.: Continuous and diverse image-to-image translation via signed attribute vectors. Int. J. Comput. Vis. (IJCV) 130, 517\u2013549 (2022)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"25_CR23","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","volume":"20","author":"A Mittal","year":"2012","unstructured":"Mittal, A., Soundararajan, R., Bovik, A.C.: Making a \u201ccompletely blind\u2019\u2019 image quality analyzer. IEEE Signal Process. Lett. 20, 209\u2013212 (2012)","journal-title":"IEEE Signal Process. Lett."},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00473"},{"key":"25_CR25","unstructured":"van den Oord, A., Kalchbrenner, N.: Pixel RNN. In: International Conference on Machine Learning (ICML) (2016)"},{"key":"25_CR26","unstructured":"van den Oord, A., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., Kavukcuoglu, K.: Conditional image generation with pixelCNN decoders. In: Advances in Neural Information Processing Systems (NeurIPS) (2016)"},{"key":"25_CR27","unstructured":"van den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"25_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-58545-7_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Park","year":"2020","unstructured":"Park, T., Efros, A.A., Zhang, R., Zhu, J.-Y.: Contrastive learning for unpaired image-to-image translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 319\u2013345. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_19"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"25_CR30","unstructured":"Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"25_CR31","unstructured":"Teterwak, P., et al.: Boundless: generative adversarial networks for image extension. In: IEEE International Conference on Computer Vision (ICCV) (2019)"},{"key":"25_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1007\/978-3-030-58598-3_15","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H-Y Tseng","year":"2020","unstructured":"Tseng, H.-Y., Lee, H.-Y., Jiang, L., Yang, M.-H., Yang, W.: RetrieveGAN: image synthesis via differentiable patch retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 242\u2013257. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_15"},{"key":"25_CR33","unstructured":"Zhang, Z., et al.: UFC-BERT: unifying multi-modal controls for conditional image synthesis (2021)"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"25_CR35","unstructured":"Zhu, J.Y., et al.: Multimodal image-to-image translation by enforcing bi-cycle consistency. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"25_CR36","unstructured":"Zhu, J.Y., et al.: Toward multimodal image-to-image translation. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"}],"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\/978-3-031-19787-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:22:18Z","timestamp":1710357738000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19787-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197864","9783031197871"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19787-1_25","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":"21 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)"}}]}}