{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:45:15Z","timestamp":1781797515958,"version":"3.54.5"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T00:00:00Z","timestamp":1738281600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T00:00:00Z","timestamp":1738281600000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s11263-025-02352-3","type":"journal-article","created":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T21:45:54Z","timestamp":1738359954000},"page":"3781-3802","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7280-249X","authenticated-orcid":false,"given":"Jiazheng","family":"Xing","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijie","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baigui","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,31]]},"reference":[{"issue":"4","key":"2352_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592450","volume":"42","author":"O Avrahami","year":"2023","unstructured":"Avrahami, O., Fried, O., & Lischinski, D. (2023). Blended latent diffusion. ACM Transactions on Graphics (TOG), 42(4), 1\u201311.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2352_CR2","doi-asserted-by":"crossref","unstructured":"Bai, S., Zhou, H., Li, Z., Zhou, C., & Yang, H. (2022). Single stage virtual try-on via deformable attention flows. In European conference on computer vision Berlin: Springer (pp. 409\u2013425).","DOI":"10.1007\/978-3-031-19784-0_24"},{"key":"2352_CR3","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Morelli, D., Cartella, G., Cornia, M., Bertini, M., & Cucchiara, R. (2023). Multimodal garment designer: Human-centric latent diffusion models for fashion image editing. arXiv preprint arXiv:2304.02051","DOI":"10.1109\/ICCV51070.2023.02138"},{"key":"2352_CR4","doi-asserted-by":"crossref","unstructured":"Bhunia, A. K., Khan, S., Cholakkal, H., Anwer, R. M., Laaksonen, J., Shah, M., & Khan, F. S. (2023). Person image synthesis via denoising diffusion model. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5968\u20135976).","DOI":"10.1109\/CVPR52729.2023.00578"},{"key":"2352_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C. Y., Chen, Y. C., Shuai, H. H., & Cheng, W. H. (2023a). Size does matter: Size-aware virtual try-on via clothing-oriented transformation try-on network. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 7513\u20137522).","DOI":"10.1109\/ICCV51070.2023.00691"},{"key":"2352_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., & Zhao, H. (2023b). Anydoor: Zero-shot object-level image customization. arXiv preprint arXiv:2307.09481","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"2352_CR7","doi-asserted-by":"crossref","unstructured":"Choi, S., Park, S., Lee, M., & Choo, J. (2021). Viton-hd: High-resolution virtual try-on via misalignment-aware normalization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14131\u201314140).","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"2352_CR8","doi-asserted-by":"crossref","unstructured":"Corneanu, C., Gadde, R., & Martinez, A. M. (2024). Latentpaint: Image in painting in latent space with diffusion models. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 4334\u20134343).","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"2352_CR9","unstructured":"Cui, A., Mahajan, J., Shah, V., Gomathinayagam, P., & Lazebnik, S. (2023). Street tryon: Learning in-the-wild virtual try-on from unpaired person images. arXiv preprint arXiv:2311.16094"},{"key":"2352_CR10","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., & Nichol, A. (2021). Diffusion models beat gans on image synthesis. Advances in neural information processing systems, 34, 8780\u20138794.","journal-title":"Advances in neural information processing systems"},{"key":"2352_CR11","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019) Dual attention network for scene segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3146\u20133154).","DOI":"10.1109\/CVPR.2019.00326"},{"key":"2352_CR12","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A. H., Chechik, G., & Cohen-Or, D. (2022). An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618"},{"key":"2352_CR13","doi-asserted-by":"crossref","unstructured":"Ge, C., Song, Y., Ge, Y., Yang, H., Liu, W., & Luo, P. (2021a). Disentangled cycle consistency for highly-realistic virtual try-on. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16928\u201316937).","DOI":"10.1109\/CVPR46437.2021.01665"},{"key":"2352_CR14","doi-asserted-by":"crossref","unstructured":"Ge, Y., Song, Y., Zhang, R., Ge, C., Liu, W., & Luo, P. (2021b). Parser-free virtual try-on via distilling appearance flows. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8485\u20138493).","DOI":"10.1109\/CVPR46437.2021.00838"},{"key":"2352_CR15","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems (Vol. 27)."},{"key":"2352_CR16","doi-asserted-by":"crossref","unstructured":"Gou, J., Sun, S., Zhang, J., Si, J., Qian, C., & Zhang, L. (2023). Taming the power of diffusion models for high-quality virtual try-on with appearance flow. arXiv preprint arXiv:2308.06101","DOI":"10.1145\/3581783.3612255"},{"key":"2352_CR17","doi-asserted-by":"crossref","unstructured":"G\u00fcler, R. A., Neverova, N., & Kokkinos, I. (2018). Densepose: Dense human pose estimation in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7297\u20137306).","DOI":"10.1109\/CVPR.2018.00762"},{"key":"2352_CR18","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. C. (2017). Improved training of wasserstein gans. In Advances in neural information processing systems (Vol. 30)."},{"key":"2352_CR19","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Wu, Z., Yu, R., & Davis, L. S. (2018). Viton: An image-based virtual try-on network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7543\u20137552).","DOI":"10.1109\/CVPR.2018.00787"},{"key":"2352_CR20","doi-asserted-by":"crossref","unstructured":"Han, X., Hu, X., Huang, W., & Scott, M. R. (2019). Clothflow: A flow-based model for clothed person generation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10471\u201310480).","DOI":"10.1109\/ICCV.2019.01057"},{"key":"2352_CR21","doi-asserted-by":"crossref","unstructured":"He, S., Song, Y. Z., & Xiang, T. (2022). Style-based global appearance flow for virtual try-on. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3470\u20133479).","DOI":"10.1109\/CVPR52688.2022.00346"},{"key":"2352_CR22","unstructured":"Ho, J., & Salimans, T. (2022). Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598"},{"key":"2352_CR23","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in neural information processing systems, 33, 6840\u20136851.","journal-title":"Advances in neural information processing systems"},{"key":"2352_CR24","doi-asserted-by":"crossref","unstructured":"Issenhuth, T., Mary, J., & Calauzenes, C. (2020). Do not mask what you do not need to mask: A parser-free virtual try-on. In Computer Vision\u2014ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part, X.X. 16. Berlin: Springer (pp. 619\u2013635).","DOI":"10.1007\/978-3-030-58565-5_37"},{"key":"2352_CR25","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8110\u20138119).","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"2352_CR26","doi-asserted-by":"crossref","unstructured":"Kim, J., Gu, G., Park, M., Park, S., & Choo, J. (2023). Stableviton: Learning semantic correspondence with latent diffusion model for virtual try-on. arXiv preprint arXiv:2312.01725","DOI":"10.1109\/CVPR52733.2024.00781"},{"key":"2352_CR27","doi-asserted-by":"crossref","unstructured":"Lee, S., Gu, G., Park, S., Choi, S., & Choo, J. (2022). High-resolution virtual try-on with misalignment and occlusion-handled conditions. In European conference on computer vision. Berlin: Springer (pp. 204\u2013219).","DOI":"10.1007\/978-3-031-19790-1_13"},{"issue":"4","key":"2352_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459884","volume":"40","author":"KM Lewis","year":"2021","unstructured":"Lewis, K. M., Varadharajan, S., & Kemelmacher-Shlizerman, I. (2021). Tryongan: Body-aware try-on via layered interpolation. ACM Transactions on Graphics (TOG), 40(4), 1\u201310.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2352_CR29","unstructured":"Li, L., Bao, J., Yang, H., Chen, D., & Wen, F. (2019). Faceshifter: Towards high fidelity and occlusion aware face swapping. arXiv preprint arXiv:1912.13457"},{"key":"2352_CR30","unstructured":"Li, X., Kampffmeyer, M., Dong, X., Xie, Z., Zhu, F., Dong, H., & Liang, X. (2023a). Warpdiffusion: Efficient diffusion model for high-fidelity virtual try-on. arXiv preprint arXiv:2312.03667"},{"key":"2352_CR31","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., Li, C., & Lee, Y. J. (2023b). Gligen: Open-set grounded text-to-image generation. In Proceedings of the, I.EEE\/CVF conference on computer vision and pattern recognition (pp. 22511\u201322521).","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"2352_CR32","doi-asserted-by":"crossref","unstructured":"Li, Z., Wei, P., Yin, X., Ma, Z., & Kot, A. C. (2023c). Virtual try-on with pose-garment keypoints guided inpainting. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 22788\u201322797).","DOI":"10.1109\/ICCV51070.2023.02083"},{"key":"2352_CR33","unstructured":"Liu, L., Ren, Y., Lin, Z., & Zhao, Z. (2022). Pseudo numerical methods for diffusion models on manifolds. arXiv preprint arXiv:2202.09778"},{"key":"2352_CR34","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3431\u20133440).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2352_CR35","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101."},{"key":"2352_CR36","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., & Van\u00a0Gool, L. (2022). Repaint: Inpainting using denoising diffusion probabilistic models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 11461\u201311471).","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"2352_CR37","first-page":"10","volume":"3","author":"MR Minar","year":"2020","unstructured":"Minar, M. R., Tuan, T. T., Ahn, H., Rosin, P., & Lai, Y. K. (2020). Cp-vton+: Clothing shape and texture preserving image-based virtual try-on. CVPR Workshops, 3, 10\u201314.","journal-title":"CVPR Workshops"},{"key":"2352_CR38","unstructured":"Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957"},{"key":"2352_CR39","doi-asserted-by":"crossref","unstructured":"Morelli, D., Fincato, M., Cornia, M., Landi, F., Cesari, F., & Cucchiara, R. (2022). Dress code: High-resolution multi-category virtual try-on. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 2231\u20132235).","DOI":"10.1109\/CVPRW56347.2022.00243"},{"key":"2352_CR40","doi-asserted-by":"crossref","unstructured":"Morelli, D., Baldrati, A., Cartella, G., Cornia, M., Bertini, M., & Cucchiara, R. (2023). Ladi-vton: Latent diffusion textual-inversion enhanced virtual try-on. arXiv preprint arXiv:2305.13501","DOI":"10.1145\/3581783.3612137"},{"key":"2352_CR41","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Zhang, J., Qi, Z., Shan, Y., & Qie, X. (2023). T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"2352_CR42","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021). Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741"},{"key":"2352_CR43","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with clip latents vol. 1(2), 3. arXiv preprint arXiv:2204.06125"},{"key":"2352_CR44","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10684\u201310695).","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2352_CR45","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K. (2023). 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 (pp. 22500\u201322510).","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"2352_CR46","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., Mahdavi, S. S., Ho, J., Fleet, D. J., & Norouzi, M. (2022). Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35, 36479\u201336494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2352_CR47","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., & Jung, H. J. (2023). Instantbooth: Personalized text-to-image generation without test-time finetuning. arXiv preprint arXiv:2304.03411","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"2352_CR48","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., & Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning, PMLR (pp. 2256\u20132265)."},{"key":"2352_CR49","unstructured":"Song, J., Meng, C., & Ermon, S. (2020). Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502"},{"key":"2352_CR50","unstructured":"Sun, K., Cao, J., Wang, Q., Tian, L., Zhang, X., Zhuo, L., Zhang, B., Bo, L., Zhou, W., Zhang, W., & Gao, D. (2024). Outfitanyone: Ultra-high quality virtual try-on for any clothing and any person. arXiv preprint arXiv:2407.16224"},{"key":"2352_CR51","doi-asserted-by":"crossref","unstructured":"Wang, B., Zheng, H., Liang, X., Chen, Y., Lin, L., & Yang, M. (2018). Toward characteristic-preserving image-based virtual try-on network. In Proceedings of the European conference on computer vision (ECCV) (pp. 589\u2013604).","DOI":"10.1007\/978-3-030-01261-8_36"},{"key":"2352_CR52","unstructured":"Wang, Q., Liu, L., Hua, M., He, Q., Zhu, P., Cao, B., & Hu, Q. (2022). Hs-diffusion: Learning a semantic-guided diffusion model for head swapping. arXiv preprint arXiv:2212.06458"},{"key":"2352_CR53","doi-asserted-by":"crossref","unstructured":"Wei Y, Zhang, Y., Ji, Z., Bai, J., Zhang, L., & Zuo, W. (2023). Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"2352_CR54","doi-asserted-by":"crossref","unstructured":"Xie, Z., Huang, Z., Dong, X., Zhao, F., Dong, H., Zhang, X., Zhu, F., & Liang, X. (2023). Gp-vton: Towards general purpose virtual try-on via collaborative local-flow global-parsing learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 23550\u201323559).","DOI":"10.1109\/CVPR52729.2023.02255"},{"key":"2352_CR55","doi-asserted-by":"crossref","unstructured":"Xu, Y., Gu, T., Chen, W., & Chen, C. (2024). Ootdiffusion: Outfitting fusion based latent diffusion for controllable virtual try-on. arXiv preprint arXiv:2403.01779","DOI":"10.1609\/aaai.v39i9.32973"},{"key":"2352_CR56","doi-asserted-by":"crossref","unstructured":"Yang, B., Gu, S., Zhang, B., Zhang, T., Chen, X., Sun, X., Chen, D., & Wen, F. (2023). Paint by example: Exemplar-based image editing with diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 18381\u201318391).","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"2352_CR57","doi-asserted-by":"crossref","unstructured":"Yang, H., Zhang, R., Guo, X., Liu, W., Zuo, W., Luo, P. (2020). Towards photo-realistic virtual try-on by adaptively generating-preserving image content. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7850\u20137859).","DOI":"10.1109\/CVPR42600.2020.00787"},{"key":"2352_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 3836\u20133847).","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2352_CR59","doi-asserted-by":"crossref","unstructured":"Zheng, N., Song, X., Chen, Z., Hu, L., Cao, D., & Nie, L. (2019). Virtually trying on new clothing with arbitrary poses. In Proceedings of the 27th ACM international conference on multimedia (pp. 266\u2013274).","DOI":"10.1145\/3343031.3350946"},{"key":"2352_CR60","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yang, D., Zhu, T., Reda, F., Chan, W., Saharia, C., Norouzi, M., & Kemelmacher-Shlizerman, I. (2023a). Tryondiffusion: A tale of two unets. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4606\u20134615).","DOI":"10.1109\/CVPR52729.2023.00447"},{"key":"2352_CR61","doi-asserted-by":"crossref","unstructured":"Zhu, S., Urtasun, R., Fidler, S., Lin, D., & Change\u00a0Loy, C. (2017). Be your own prada: Fashion synthesis with structural coherence. In Proceedings of the IEEE international conference on computer vision (pp. 1680\u20131688).","DOI":"10.1109\/ICCV.2017.186"},{"key":"2352_CR62","unstructured":"Zhu, Z., Feng, X., Chen, D., Bao, J., Wang, L., Chen, Y., Yuan, L., & Hua, G. (2023b). Designing a better asymmetric vqgan for stablediffusion. arXiv preprint arXiv:2306.04632"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02352-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02352-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02352-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:55:15Z","timestamp":1746860115000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02352-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,31]]},"references-count":62,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2352"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02352-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,31]]},"assertion":[{"value":"30 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}