{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:35:24Z","timestamp":1743003324939,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030926588"},{"type":"electronic","value":"9783030926595"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-92659-5_45","type":"book-chapter","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T07:09:18Z","timestamp":1642057758000},"page":"697-711","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Full-Glow: Fully Conditional Glow for\u00a0More Realistic Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6204-0778","authenticated-orcid":false,"given":"Moein","family":"Sorkhei","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1643-1054","authenticated-orcid":false,"given":"Gustav Eje","family":"Henter","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5750-9655","authenticated-orcid":false,"given":"Hedvig","family":"Kjellstr\u00f6m","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,13]]},"reference":[{"key":"45_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/978-3-030-71278-5_27","volume-title":"Pattern Recognition","author":"L Ardizzone","year":"2021","unstructured":"Ardizzone, L., Kruse, J., L\u00fcth, C., Bracher, N., Rother, C., K\u00f6the, U.: Conditional invertible neural networks for diverse image-to-image translation. In: Akata, Z., Geiger, A., Sattler, T. (eds.) DAGM GCPR 2020. LNCS, vol. 12544, pp. 373\u2013387. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-71278-5_27"},{"key":"45_CR2","unstructured":"Ardizzone, L., L\u00fcth, C., Kruse, J., Rother, C., K\u00f6the, U.: Guided image generation with conditional invertible neural networks. arXiv preprint arXiv:1907.02392 (2019)"},{"key":"45_CR3","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (2019)"},{"issue":"2","key":"45_CR4","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"Brostow, G.J., Fauqueur, J., Cipolla, R.: Semantic object classes in video: a high-definition ground truth database. Pattern Recogn. Lett. 30(2), 88\u201397 (2009)","journal-title":"Pattern Recogn. Lett."},{"key":"45_CR5","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: Neural Information Processing Systems, pp. 1877\u20131901 (2020)"},{"key":"45_CR6","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 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"45_CR7","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: NICE: non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014)"},{"key":"45_CR8","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using Real NVP. In: International Conference on Learning Representations (2017)"},{"issue":"11","key":"45_CR9","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"45_CR10","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Neural Information Processing Systems (2014)"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Grover, A., Dhar, M., Ermon, S.: Flow-GAN: combining maximum likelihood and adversarial learning in generative models. In: AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11829"},{"key":"45_CR12","unstructured":"Ho, J., Chen, X., Srinivas, A., Duan, Y., Abbeel, P.: Flow++: improving flow-based generative models with variational dequantization and architecture design. arXiv preprint arXiv:1902.00275 (2019)"},{"key":"45_CR13","unstructured":"Holtzman, A., Buys, J., Du, L., Forbes, M., Choi, Y.: The curious case of neural text degeneration. In: International Conference on Learning Representations (2020)"},{"key":"45_CR14","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"key":"45_CR15","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 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"45_CR17","unstructured":"Kim, S., Lee, S., Song, J., Kim, J., Yoon, S.: FloWaveNet: a generative flow for raw audio. In: International Conference on Machine Learning (2019)"},{"key":"45_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"45_CR19","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible $$1\\times 1$$ convolutions. In: Neural Information Processing Systems (2018)"},{"key":"45_CR20","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: International Conference on Learning Representations (2014)"},{"key":"45_CR21","unstructured":"Kumar, M., et al.: VideoFlow: a flow-based generative model for video. arXiv preprint arXiv:1903.01434 (2019)"},{"key":"45_CR22","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Lu, Y., Huang, B.: Structured output learning with conditional generative flows. In: AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i04.5940"},{"key":"45_CR24","unstructured":"Lucas, T., Shmelkov, K., Alahari, K., Schmid, C., Verbeek, J.: Adaptive density estimation for generative models. In: Neural Information Processing Systems, pp. 11993\u201312003 (2019)"},{"key":"45_CR25","unstructured":"Minka, T.: Divergence measures and message passing. Technical report, MSR-TR-2005-173, Microsoft Research, Cambridge, UK (2005)"},{"key":"45_CR26","unstructured":"van den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., Kavukcuoglu, K.: Conditional image generation with pixelCNN decoders. In: Neural Information Processing Systems (2016)"},{"key":"45_CR27","unstructured":"van den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. arXiv preprint arXiv:1601.06759 (2016)"},{"key":"45_CR28","unstructured":"Papamakarios, G., Nalisnick, E., Rezende, D.J., Mohamed, S., Lakshminarayanan, B.: Normalizing flows for probabilistic modeling and inference. arXiv preprint arXiv:1912.02762 (2019)"},{"key":"45_CR29","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS 2017 Workshop Autodiff (2017)"},{"key":"45_CR30","doi-asserted-by":"crossref","unstructured":"Prenger, R., Valle, R., Catanzaro, B.: WaveGlow: a flow-based generative network for speech synthesis. In: IEEE International Conference on Acoustics, Speech and Signal Processing (2019)","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"45_CR31","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Popov, S., Moreno-Noguer, F., Ferrari, V.: C-Flow: conditional generative flow models for images and 3D point clouds. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00797"},{"key":"45_CR32","unstructured":"Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Neural Information Processing Systems (2019)"},{"key":"45_CR33","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: International Conference on Machine Learning (2014)"},{"key":"45_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-46475-6_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"SR Richter","year":"2016","unstructured":"Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102\u2013118. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_7"},{"key":"45_CR35","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.352"},{"key":"45_CR36","doi-asserted-by":"crossref","unstructured":"Sun, H., et al.: DUAL-GLOW: conditional flow-based generative model for modality transfer. In: IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.01071"},{"key":"45_CR37","unstructured":"Theis, L., van den Oord, A., Bethge, M.: A note on the evaluation of generative models. In: International Conference on Learning Representations (2016)"},{"key":"45_CR38","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. In: Proceedings of the Allerton Conference on Communication, Control and Computing, vol. 37, pp. 368\u2013377 (2000)"},{"key":"45_CR39","unstructured":"Tsirikoglou, A., Kronander, J., Wrenninge, M., Unger, J.: Procedural modeling and physically based rendering for synthetic data generation in automotive applications. arXiv preprint arXiv:1710.06270 (2017)"},{"key":"45_CR40","unstructured":"Vahdat, A., Kautz, J.: NVAE: a deep hierarchical variational autoencoder. arXiv preprint arXiv:2007.03898 (2020)"},{"key":"45_CR41","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"45_CR42","unstructured":"Zhang, H., Dauphin, Y.N., Ma, T.: Fixup initialization: residual learning without normalization. In: International Conference on Learning Representations (2019)"},{"key":"45_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"45_CR44","unstructured":"Zhao, S., Song, J., Ermon, S.: Towards deeper understanding of variational autoencoding models. arXiv preprint arXiv:1702.08658 (2017)"},{"key":"45_CR45","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 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92659-5_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T20:29:20Z","timestamp":1674419360000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92659-5_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030926588","9783030926595"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92659-5_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"13 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"While our results are promising, further work remains to be done in order to close the gap between synthetic images and real-world photographs, for instance by adding self-attention [] and by leveraging approaches that combine the strong points of Full-Glow with the advantages of GANs, e.g., following [,]. That said, we believe the quality of the synthetic images is already at a level where it also is worth exploring their utility in training systems for autonomous cars and other mobile agents, which remains to be observed in future works.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Future Work"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bonn","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dagm-gcpr.de\/","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":"116","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":"46","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":"40% - 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":"2.95","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":"4.3","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","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)"}}]}}