{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:41:38Z","timestamp":1777657298297,"version":"3.51.4"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730030","type":"print"},{"value":"9783031730047","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73004-7_6","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:02:14Z","timestamp":1730394134000},"page":"87-103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Tackling Structural Hallucination in\u00a0Image Translation with\u00a0Local Diffusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8456-8448","authenticated-orcid":false,"given":"Seunghoi","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2179-6445","authenticated-orcid":false,"given":"Chen","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Tom","family":"Diethe","sequence":"additional","affiliation":[]},{"given":"Matteo","family":"Figini","sequence":"additional","affiliation":[]},{"given":"Henry F. J.","family":"Tregidgo","sequence":"additional","affiliation":[]},{"given":"Asher","family":"Mullokandov","sequence":"additional","affiliation":[]},{"given":"Philip","family":"Teare","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2439-350X","authenticated-orcid":false,"given":"Daniel C.","family":"Alexander","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTec AD \u2013 a comprehensive real-world dataset for unsupervised anomaly detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9584\u20139592 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00982","DOI":"10.1109\/CVPR.2019.00982"},{"key":"6_CR2","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=B1xsqj09Fm"},{"key":"6_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 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"6_CR4","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186 (2023)"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Choi, J., Lee, J., Shin, C., Kim, S., Kim, H., Yoon, S.: Perception prioritized training of diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11462\u201311471 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01118","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"6_CR6","unstructured":"Chung, H., Sim, B., Ye, J.C.: Improving diffusion models for inverse problems using manifold constraints. In: Advances in Neural Information Processing Systems (2022)"},{"issue":"6","key":"6_CR7","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141\u2013142 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"6_CR8","unstructured":"Dhariwal, P., Alex, N.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems (2021)"},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion (2022). https:\/\/doi.org\/10.48550\/ARXIV.2208.01618","DOI":"10.48550\/ARXIV.2208.01618"},{"key":"6_CR10","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 6840\u20136851 (2020)"},{"key":"6_CR11","unstructured":"Jalal, A., Arvinte, M., Daras, G., Price, E., Dimakis, A.G., Tamir, J.: Robust compressed sensing MRI with deep generative priors. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 14938\u201314954 (2021)"},{"key":"6_CR12","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 (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"6_CR13","unstructured":"Kawar, B., Elad, M., Ermon, S., Song, J.: Denoising diffusion restoration models. In: Advances in Neural Information Processing Systems (2022)"},{"key":"6_CR14","unstructured":"Kim, S., Alexander, D.C.: AGCN: adversarial graph convolutional network for 3D point cloud segmentation. In: British Machine Vision Conference (2021)"},{"key":"6_CR15","unstructured":"Kim, S., Tregidgo, H.F., Eldaly, A.K., Figini, M., Alexander, D.C.: A 3D conditional diffusion model for image quality transfer\u2013an application to low-field MRI. arXiv preprint arXiv:2311.06631 (2023)"},{"key":"6_CR16","unstructured":"Kingma, D.P., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. In: Advances in Neural Information Processing Systems (2021)"},{"key":"6_CR17","unstructured":"Koo, H.: A survey on generative diffusion models for structured data. arXiv preprint arXiv:2306.04139 (2023)"},{"key":"6_CR18","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neucom.2022.01.029","volume":"479","author":"H Li","year":"2022","unstructured":"Li, H., et al.: SRDiff: single image super-resolution with diffusion probabilistic models. Neurocomputing 479, 47\u201359 (2022)","journal-title":"Neurocomputing"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Gool, L.V.: Repaint: inpainting using denoising diffusion probabilistic models. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11451\u201311461 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"6_CR20","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2022)"},{"key":"6_CR21","unstructured":"Menze, B.H., Jakab, A., Bauer, S., et\u00a0al.: The multimodal brain tumor image segmentation benchmark (brats). IEEE Trans. Med. Imaging (2015). Please add volume and issue number, and pages information if available"},{"key":"6_CR22","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8162\u20138171 (2021)"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10674\u201310685 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01042, https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52688.2022.01042","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"6_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Roth, K., Pemula, L., Zepeda, J., Sch\u00f6lkopf, B., Brox, T., Gehler, P.: Towards total recall in industrial anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14298\u201314308 (2022)","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: In: Photorealistic text-to-image diffusion models with deep language understanding (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"6_CR28","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: International Conference on Learning Representations (2022)"},{"key":"6_CR29","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"6_CR30","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. arXiv preprint arXiv:2303.01469 (2023)"},{"key":"6_CR31","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Deep image prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)"},{"key":"6_CR32","unstructured":"Wang, Y., Yu, J., Zhang, J.: Zero-shot image restoration using denoising diffusion null-space model. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"6_CR33","unstructured":"Wang, Z., Zheng, H., He, P., Chen, W., Zhou, M.: Diffusion-GAN: training GANs with diffusion. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"6_CR34","unstructured":"Xiao, Z., Kreis, K., Vahdat, A.: Tackling the generative learning trilemma with denoising diffusion GANs. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Yu, R., Liu, S., Yang, X., Wang, X.: Distribution shift inversion for out-of-distribution prediction. In: The IEEE\/CVF Computer Vision and Pattern Recognition Conference (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00350"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. In: BMVC (2016)","DOI":"10.5244\/C.30.87"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"6_CR38","unstructured":"Zhang, M., Zhang, A., McDonagh, S.G.: On the out-of-distribution generalization of probabilistic image modelling. In: Neural Information Processing Systems (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\/978-3-031-73004-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:03:59Z","timestamp":1730394239000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73004-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031730030","9783031730047"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73004-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}