{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:54:14Z","timestamp":1781798054159,"version":"3.54.5"},"reference-count":181,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-026-21698-5","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T05:04:59Z","timestamp":1779080699000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Unpaired image-to-image translation with content preserving perspective: a review"],"prefix":"10.1007","volume":"85","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1399-1803","authenticated-orcid":false,"given":"Mehran","family":"Safayani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Behnaz","family":"Mirzapour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanieh","family":"Aghaebrahimiyan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nasrin","family":"Salehi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"Ravaee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"21698_CR1","doi-asserted-by":"crossref","unstructured":"Zhu J, Park T, Isola P, Efros A (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223\u20132232","DOI":"10.1109\/ICCV.2017.244"},{"key":"21698_CR2","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J, Zhou T, Efros A (2017) Image-to-image translation with conditional adversarial networks. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition, pp 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"21698_CR3","doi-asserted-by":"crossref","unstructured":"Tomei M, Cornia M, Baraldi L, Cucchiara R (2019) Art2real: Unfolding the reality of artworks via semantically-aware image-to-image translation. In: Proceedings Of The IEEE\/CVF conference on computer vision and pattern recognition, pp 5849\u20135859","DOI":"10.1109\/CVPR.2019.00600"},{"key":"21698_CR4","doi-asserted-by":"crossref","unstructured":"Chang H, Wang Z, Chuang Y (2020) Domain-specific mappings for generative adversarial style transfer. Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VIII 16, pp 573\u2013589","DOI":"10.1007\/978-3-030-58598-3_34"},{"key":"21698_CR5","doi-asserted-by":"crossref","unstructured":"Kumar P, Gupta V (2023) Unpaired image-to-image translation based artwork restoration using generative adversarial networks. Int Conf Intell Manuf Energy Sustain, pp 581\u2013591","DOI":"10.1007\/978-981-99-6774-2_52"},{"key":"21698_CR6","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.ifacol.2019.12.287","volume":"52","author":"Y Cho","year":"2019","unstructured":"Cho Y, Malav R, Pandey G, Kim A (2019) DehazeGAN: underwater haze image restoration using unpaired image-to-image translation. IFAC-PapersOnLine 52:82\u201385","journal-title":"IFAC-PapersOnLine"},{"key":"21698_CR7","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.neucom.2019.01.115","volume":"394","author":"X Guo","year":"2020","unstructured":"Guo X, Wang Z, Yang Q, Lv W, Liu X, Wu Q, Huang J (2020) GAN-based virtual-to-real image translation for urban scene semantic segmentation. Neurocomputing 394:127\u2013135","journal-title":"Neurocomputing"},{"issue":"107343","key":"21698_CR8","first-page":"1","volume":"105","author":"R Li","year":"2020","unstructured":"Li R, Cao W, Jiao Q, Wu S, Wong H (2020) Simplified unsupervised image translation for semantic segmentation adaptation. Pattern Recogn 105(107343):1\u201312","journal-title":"Pattern Recogn"},{"key":"21698_CR9","doi-asserted-by":"crossref","unstructured":"Murez Z, Kolouri S, Kriegman D, Ramamoorthi R, Kim K (2018) Image to image translation for domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4500\u20134509","DOI":"10.1109\/CVPR.2018.00473"},{"key":"21698_CR10","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1109\/TNNLS.2018.2868854","volume":"30","author":"J Li","year":"2018","unstructured":"Li J, Lu K, Huang Z, Zhu L, Shen H (2018) Heterogeneous domain adaptation through progressive alignment. IEEE Trans Neural Netw Learn Syst 30:1381\u20131391","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"21698_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3400066","volume":"11","author":"G Wilson","year":"2020","unstructured":"Wilson G, Cook D (2020) A survey of unsupervised deep domain adaptation. ACM Transactions On Intelligent Systems And Technology (TIST) 11:1\u201346","journal-title":"ACM Transactions On Intelligent Systems And Technology (TIST)"},{"key":"21698_CR12","doi-asserted-by":"crossref","unstructured":"Lee H, Tseng H, Huang J, Singh M, Yang M (2018) Diverse image-to-image translation via disentangled representations. In: Proceedings of the European Conference On Computer Vision (ECCV), pp 35\u201351","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"21698_CR13","doi-asserted-by":"crossref","unstructured":"Yi Z, Zhang H, Tan P, Gong M (2017) Dualgan: Unsupervised dual learning for image-to-image translation. In: Proceedings of the IEEE international conference on computer vision, pp 2849\u20132857","DOI":"10.1109\/ICCV.2017.310"},{"key":"21698_CR14","doi-asserted-by":"crossref","unstructured":"Huang X, Liu M, Belongie S, Kautz J (2018) Multimodal unsupervised image-to-image translation. In: Proceedings Of The European Conference On Computer Vision (ECCV), pp 172\u2013189","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"21698_CR15","doi-asserted-by":"publisher","first-page":"3859","DOI":"10.1109\/TMM.2021.3109419","volume":"24","author":"Y Pang","year":"2021","unstructured":"Pang Y, Lin J, Qin T, Chen Z (2021) Image-to-image translation: Methods and applications. IEEE Trans Multimedia 24:3859\u20133881","journal-title":"IEEE Trans Multimedia"},{"key":"21698_CR16","doi-asserted-by":"crossref","unstructured":"Cho W, Choi S, Park D, Shin I, Choo J (2019) Image-to-image translation via group-wise deep whitening-and-coloring transformation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10639\u201310647","DOI":"10.1109\/CVPR.2019.01089"},{"key":"21698_CR17","doi-asserted-by":"crossref","unstructured":"Theiss J, Leverett J, Kim D, Prakash A (2022) Unpaired image translation via vector symbolic architectures. Eur Conf Comput Vision, pp 17\u201332","DOI":"10.1007\/978-3-031-19803-8_2"},{"key":"21698_CR18","unstructured":"Fan W, Chen J, Ma J, Hou J, Yi S (2022) Styleflow for content-fixed image to image translation. ArXiv Preprint ArXiv:2207.01909"},{"key":"21698_CR19","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.neucom.2018.05.083","volume":"312","author":"M Wang","year":"2018","unstructured":"Wang M, Deng W (2018) Deep visual domain adaptation: A survey. Neurocomputing 312:135\u2013153","journal-title":"Neurocomputing"},{"key":"21698_CR20","doi-asserted-by":"publisher","first-page":"7327","DOI":"10.1109\/TPAMI.2021.3116668","volume":"44","author":"S Bond-Taylor","year":"2021","unstructured":"Bond-Taylor S, Leach A, Long Y, Willcocks C (2021) Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models. IEEE Trans Patt Anal Mach Intell 44:7327\u20137347","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"21698_CR21","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1109\/TNNLS.2020.3028503","volume":"33","author":"S Zhao","year":"2020","unstructured":"Zhao S, Yue X, Zhang S, Li B, Zhao H, Wu B, Krishna R, Gonzalez J, Sangiovanni-Vincentelli A, Seshia S, Keutzer K (2020) A review of single-source deep unsupervised visual domain adaptation. IEEE Trans Neural Netw Learn Syst 33:473\u2013493","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"21698_CR22","doi-asserted-by":"crossref","unstructured":"Farahani A, Voghoei S, Rasheed K, Arabnia H (2021) A brief review of domain adaptation. Advances In Data Science And Information Engineering: Proceedings From ICDATA 2020 And IKE 2020, pp 877\u2013894","DOI":"10.1007\/978-3-030-71704-9_65"},{"key":"21698_CR23","unstructured":"Saxena S, Teli M (2021) Comparison and analysis of image-to-image generative adversarial networks: a survey. ArXiv Preprint ArXiv:2112.12625"},{"key":"21698_CR24","first-page":"8540","volume":"22","author":"H Hoyez","year":"2022","unstructured":"Hoyez H, Schockaert C, Rambach J, Mirbach B, Stricker D (2022) Unsupervised image-to-image translation A review Sensors 22:8540","journal-title":"Unsupervised image-to-image translation A review Sensors"},{"key":"21698_CR25","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3724\/SP.J.1089.2024.19807","volume":"36","author":"T Hangyao","year":"2024","unstructured":"Hangyao T, Wanliang W, Jiacheng C, Guoqing L, Fei W (2024) A Survey of Image Translation Based on Conditional Generative Adversarial Networks. J Comput-Aided Design Comput Graphics 36:14\u201332","journal-title":"J Comput-Aided Design Comput Graphics"},{"key":"21698_CR26","doi-asserted-by":"crossref","unstructured":"Wang T (2025) A Comprehensive Review of Image-to-Image Translation, Face Manipulation, and Neural Style Transfer Methods. Authorea Preprints","DOI":"10.36227\/techrxiv.174431621.17773362\/v1"},{"key":"21698_CR27","doi-asserted-by":"crossref","unstructured":"Fu H, Gong M, Wang C, Batmanghelich K, Zhang K, Tao D (2019) Geometry-consistent generative adversarial networks for one-sided unsupervised domain mapping. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2427\u20132436","DOI":"10.1109\/CVPR.2019.00253"},{"key":"21698_CR28","doi-asserted-by":"crossref","unstructured":"Chen R, Huang W, Huang B, Sun F, Fang B (2020) Reusing discriminators for encoding: Towards unsupervised image-to-image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8168\u20138177","DOI":"10.1109\/CVPR42600.2020.00819"},{"key":"21698_CR29","doi-asserted-by":"crossref","unstructured":"Xie S, Gong M, Xu Y, Zhang K (2021) Unaligned image-to-image translation by learning to reweight. In: Proceedings Of The IEEE\/CVF international conference on computer vision, pp 14174\u201314184","DOI":"10.1109\/ICCV48922.2021.01391"},{"key":"21698_CR30","doi-asserted-by":"crossref","unstructured":"Tobin J, Fong R, Ray A, Schneider J, Zaremba W, Abbeel P (2017) Domain randomization for transferring deep neural networks from simulation to the real world. 2017 IEEE\/RSJ International Conference On Intelligent Robots And Systems (IROS), pp 23\u201330","DOI":"10.1109\/IROS.2017.8202133"},{"key":"21698_CR31","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. Adv Neural Inf Proc Syst 27"},{"key":"21698_CR32","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2018","unstructured":"Zhang H, Xu T, Li H, Zhang S, Wang X, Huang X, Metaxas D (2018) Stackgan++: Realistic image synthesis with stacked generative adversarial networks. IEEE Trans Patt Anal Mach Intell 41:1947\u20131962","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"21698_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108098","volume":"119","author":"G De Rosa","year":"2021","unstructured":"De Rosa G, Papa J (2021) A survey on text generation using generative adversarial networks. Pattern Recogn 119:108098","journal-title":"Pattern Recogn"},{"key":"21698_CR34","doi-asserted-by":"crossref","unstructured":"Liu Z, Wang J, Liang Z (2020) Catgan: Category-aware generative adversarial networks with hierarchical evolutionary learning for category text generation. In: Proceedings of the AAAI conference on artificial intelligence 34:8425\u20138432","DOI":"10.1609\/aaai.v34i05.6361"},{"key":"21698_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3487891","volume":"55","author":"N Aldausari","year":"2022","unstructured":"Aldausari N, Sowmya A, Marcus N, Mohammadi G (2022) Video generative adversarial networks: a review. ACM Computing Surveys (CSUR) 55:1\u201325","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"21698_CR36","doi-asserted-by":"publisher","first-page":"7454","DOI":"10.1109\/TIP.2020.3003227","volume":"29","author":"Q Chen","year":"2020","unstructured":"Chen Q, Wu Q, Chen J, Wu Q, Hengel A, Tan M (2020) Scripted video generation with a bottom-up generative adversarial network. IEEE Trans Image Process 29:7454\u20137467","journal-title":"IEEE Trans Image Process"},{"key":"21698_CR37","unstructured":"Mirza M (2014) Conditional generative adversarial nets. ArXiv Preprint ArXiv:1411.1784"},{"key":"21698_CR38","unstructured":"Gauthier J (2014) Conditional generative adversarial nets for convolutional face generation. Class Project For Stanford CS231N: Convolutional Neural Networks For Visual Recognition, Winter Semester 2014:2"},{"key":"21698_CR39","unstructured":"Kingma D (2013) Auto-encoding variational bayes. ArXiv Preprint ArXiv:1312.6114"},{"key":"21698_CR40","doi-asserted-by":"crossref","unstructured":"Pumarola A, Popov S, Moreno-Noguer F, Ferrari V (2020) C-flow: Conditional generative flow models for images and 3d point clouds. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7949\u20137958","DOI":"10.1109\/CVPR42600.2020.00797"},{"key":"21698_CR41","unstructured":"Rezende D, Mohamed S (2015) Variational inference with normalizing flows. Int Conf Mach Learn, pp 1530\u20131538"},{"key":"21698_CR42","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inf Process Syst 33:6840\u20136851","journal-title":"Adv Neural Inf Process Syst"},{"key":"21698_CR43","unstructured":"Sasaki H, Willcocks C, Breckon T (2021) Unit-ddpm: Unpaired image translation with denoising diffusion probabilistic models. ArXiv Preprint ArXiv:2104.05358"},{"key":"21698_CR44","first-page":"3609","volume":"35","author":"M Zhao","year":"2022","unstructured":"Zhao M, Bao F, Li C, Zhu J (2022) Egsde: Unpaired image-to-image translation via energy-guided stochastic differential equations. Adv Neural Inf Process Syst 35:3609\u20133623","journal-title":"Adv Neural Inf Process Syst"},{"key":"21698_CR45","unstructured":"Meng C, He Y, Song Y, Song J, Wu J, Zhu J, Ermon S (2022) SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations"},{"key":"21698_CR46","unstructured":"Kim B, Kwon G, Kim K, Ye J (2023) Unpaired Image-to-Image Translation via Neural Schrodinger Bridge. ArXiv Preprint ArXiv:2305.15086"},{"key":"21698_CR47","unstructured":"Vaswani A (2017) Attention is all you need. Adv Neural Inf Proc Syst"},{"key":"21698_CR48","unstructured":"Alexey D (2020) An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv Preprint ArXiv:2010.11929"},{"key":"21698_CR49","doi-asserted-by":"crossref","unstructured":"Ranftl R, Bochkovskiy A, Koltun V (2021) Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 12179\u201312188","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"21698_CR50","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han K, Wang Y et al (2022) A survey on vision transformer. IEEE Trans Patt Anal Mach Intell 45:87\u2013110","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"21698_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"S Khan","year":"2022","unstructured":"Khan S, Naseer M, Hayat M, Zamir S, Khan F, Shah M (2022) Transformers in vision: A survey. ACM Computing Surveys (CSUR) 54:1\u201341","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"21698_CR52","unstructured":"Dosovitskiy A, Beyer L et al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv Preprint ArXiv:2010.11929"},{"key":"21698_CR53","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.neucom.2019.03.011","volume":"341","author":"L Liu","year":"2019","unstructured":"Liu L, Zhang H, Ji Y, Wu Q (2019) Toward AI fashion design: An Attribute-GAN model for clothing match. Neurocomputing 341:156\u2013167","journal-title":"Neurocomputing"},{"key":"21698_CR54","doi-asserted-by":"crossref","unstructured":"Moosaei M, Lin Y, Akhazhanov A, Chen H, Wang F, Yang H (2022) Outfitgan: Learning compatible items for generative fashion outfits. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2273\u20132277","DOI":"10.1109\/CVPRW56347.2022.00251"},{"key":"21698_CR55","doi-asserted-by":"publisher","first-page":"4986","DOI":"10.1109\/TMM.2022.3185894","volume":"25","author":"D Zhou","year":"2022","unstructured":"Zhou D, Zhang H, Li Q, Ma J, Xu X (2022) Coutfitgan: learning to synthesize compatible outfits supervised by silhouette masks and fashion styles. IEEE Trans Multimedia 25:4986\u20135001","journal-title":"IEEE Trans Multimedia"},{"key":"21698_CR56","doi-asserted-by":"publisher","first-page":"3245","DOI":"10.1109\/TCSVT.2023.3318216","volume":"34","author":"D Zhou","year":"2023","unstructured":"Zhou D, Zhang H, Ma J, Shi J (2023) BC-GAN: A generative adversarial network for synthesizing a batch of collocated clothing. IEEE Trans Circuits Syst Video Technol 34:3245\u20133259","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"21698_CR57","doi-asserted-by":"crossref","unstructured":"Dong M, Zhou D, Ma J, Zhang H (2024) Towards intelligent design: A self-driven framework for collocated clothing synthesis leveraging fashion styles and textures. ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 3725\u20133729","DOI":"10.1109\/ICASSP48485.2024.10446336"},{"key":"21698_CR58","doi-asserted-by":"crossref","unstructured":"Zhou D, Zhang H, Ma J, Fan J, Zhang Zh (2023) Fcboost-net: A generative network for synthesizing multiple collocated outfits via fashion compatibility boosting. In: Proceedings of the 31st ACM international conference on multimedia, pp 7881\u20137889","DOI":"10.1145\/3581783.3612036"},{"key":"21698_CR59","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":"21698_CR60","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. Eur Conf Comput Vision, pp 204\u2013219","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"21698_CR61","unstructured":"Kim T, Cha M, Kim H, Lee J, Kim J (2017) Learning to discover cross-domain relations with generative adversarial networks. Int Conf Mach Learn, pp 1857\u20131865"},{"key":"21698_CR62","unstructured":"Benaim S, Wolf L (2017) One-sided unsupervised domain mapping. Adv Neural Inf Proc Syst 30"},{"key":"21698_CR63","unstructured":"Arjovsky M, Chintala S, Bottou L, Wasserstein (2017) generative adversarial networks. Int Conf Mach Learn, pp 214\u2013223"},{"key":"21698_CR64","unstructured":"Ma L, Jia X, Georgoulis S, Tuytelaars T, Van Gool L (2018) Exemplar guided unsupervised image-to-image translation with semantic consistency. ArXiv Preprint ArXiv:1805.11145"},{"key":"21698_CR65","doi-asserted-by":"crossref","unstructured":"Park T, Liu M, Wang T, Zhu J (2019) Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2337\u20132346","DOI":"10.1109\/CVPR.2019.00244"},{"key":"21698_CR66","doi-asserted-by":"crossref","unstructured":"Jia Z, Yuan B, Wang K, Wu H, Clifford D, Yuan Z, Su H (2021) Semantically robust unpaired image translation for data with unmatched semantics statistics. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 14273\u201314283","DOI":"10.1109\/ICCV48922.2021.01401"},{"key":"21698_CR67","doi-asserted-by":"crossref","unstructured":"Zheng C, Cham T, Cai J (2021) The spatially-correlative loss for various image translation tasks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16407\u201316417","DOI":"10.1109\/CVPR46437.2021.01614"},{"key":"21698_CR68","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1109\/TMM.2020.2975961","volume":"23","author":"H Emami","year":"2020","unstructured":"Emami H, Aliabadi M, Dong M, Chinnam R (2020) SPA-GAN: Spatial attention GAN for image-to-image translation. IEEE Trans Multimedia 23:391\u2013401","journal-title":"IEEE Trans Multimedia"},{"key":"21698_CR69","first-page":"800","volume":"16","author":"Y Zhao","year":"2020","unstructured":"Zhao Y, Wu R, Dong H (2020) Unpaired image-to-image translation using adversarial consistency loss. Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020. Proceedings Part IX 16:800\u2013815","journal-title":"Proceedings Part IX"},{"key":"21698_CR70","doi-asserted-by":"crossref","unstructured":"Liu Y, Wang H, Yue Y, Lu F (2021) Separating content and style for unsupervised image-to-image translation. ArXiv Preprint ArXiv:2110.14404","DOI":"10.5244\/C.35.91"},{"key":"21698_CR71","doi-asserted-by":"crossref","unstructured":"Huang X, Belongie S (2017) Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE international conference on computer vision, pp 1501\u20131510","DOI":"10.1109\/ICCV.2017.167"},{"key":"21698_CR72","doi-asserted-by":"crossref","unstructured":"Zhou X, Zhang B, Zhang T, Zhang P, Bao J, Chen D, Zhang Z, Wen F (2021) Cocosnet v2: Full-resolution correspondence learning for image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11465\u201311475","DOI":"10.1109\/CVPR46437.2021.01130"},{"key":"21698_CR73","first-page":"319","volume":"16","author":"T Park","year":"2020","unstructured":"Park T, Efros A, Zhang R, Zhu J (2020) Contrastive learning for unpaired image-to-image translation. Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020. Proceedings Part IX 16:319\u2013345","journal-title":"Proceedings Part IX"},{"key":"21698_CR74","doi-asserted-by":"crossref","unstructured":"Han J, Shoeiby M, Petersson L, Armin M (2021) Dual contrastive learning for unsupervised image-to-image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 746\u2013755","DOI":"10.1109\/CVPRW53098.2021.00084"},{"key":"21698_CR75","doi-asserted-by":"crossref","unstructured":"Wang W, Zhou W, Bao J, Chen D, Li H (2021) Instance-wise hard negative example generation for contrastive learning in unpaired image-to-image translation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 14020\u201314029","DOI":"10.1109\/ICCV48922.2021.01376"},{"key":"21698_CR76","doi-asserted-by":"crossref","unstructured":"Pizzati F, Lalonde J, Charette R (2022) Manifest: Manifold deformation for few-shot image translation. Eur Conf Comput Vision, pp 440\u2013456","DOI":"10.1007\/978-3-031-19790-1_27"},{"key":"21698_CR77","doi-asserted-by":"crossref","unstructured":"Lin J, Wang Y, Chen Z, He T (2020) Learning to transfer: unsupervised domain translation via meta-learning. In: Proceedings of the AAAI conference on artificial intelligence 34:11507\u201311514","DOI":"10.1609\/aaai.v34i07.6816"},{"key":"21698_CR78","doi-asserted-by":"crossref","unstructured":"Koksal A, Lu S (2020) Rf-gan: A light and reconfigurable network for unpaired image-to-image translation. In: Proceedings of the Asian conference on computer vision","DOI":"10.1007\/978-3-030-69538-5_33"},{"key":"21698_CR79","unstructured":"Ye K, Ye Y, Yang M, Hu B (2021) Independent encoder for deep hierarchical unsupervised image-to-image translation. ArXiv Preprint ArXiv:2107.02494"},{"key":"21698_CR80","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.neucom.2022.07.084","volume":"506","author":"J Zhao","year":"2022","unstructured":"Zhao J, Lee F, Hu C, Yu H, Chen Q (2022) LDA-GAN: Lightweight domain-attention GAN for unpaired image-to-image translation. Neurocomputing 506:355\u2013368","journal-title":"Neurocomputing"},{"key":"21698_CR81","doi-asserted-by":"publisher","first-page":"16593","DOI":"10.1007\/s00521-023-08530-z","volume":"35","author":"H Deng","year":"2023","unstructured":"Deng H, Wu Q, Huang H, Yang X, Wang Z (2023) InvolutionGAN: lightweight GAN with involution for unsupervised image-to-image translation. Neural Comput Appl 35:16593\u201316605","journal-title":"Neural Comput Appl"},{"key":"21698_CR82","unstructured":"Gong Y, Zhan Z, Jin Q, Li Y, Idelbayev Y, Liu X, Zharkov A, Aberman K, Tulyakov S, Wang Y et al(2024) E 2 GAN: Efficient Training of Efficient GANs for Image-to-Image Translation. ArXiv Preprint ArXiv:2401.06127"},{"key":"21698_CR83","unstructured":"Ouderaa T, Worrall D (2019) Reversible gans for memory-efficient image-to-image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4720\u20134728"},{"key":"21698_CR84","doi-asserted-by":"publisher","first-page":"3180","DOI":"10.1109\/TMM.2022.3156699","volume":"25","author":"S Li","year":"2022","unstructured":"Li S, Lin M, Wang Y, Chao F, Shao L, Ji R (2022) Learning efficient gans for image translation via differentiable masks and co-attention distillation. IEEE Trans Multimedia 25:3180\u20133189","journal-title":"IEEE Trans Multimedia"},{"key":"21698_CR85","doi-asserted-by":"crossref","unstructured":"Ganjdanesh A, Gao S, Alipanah H, Huang H (2024) Compressing image-to-image translation gans using local density structures on their learned manifold. In: Proceedings of the AAAI conference on artificial intelligence 38:12118\u201312126","DOI":"10.1609\/aaai.v38i11.29100"},{"key":"21698_CR86","doi-asserted-by":"crossref","unstructured":"Amodio M, Krishnaswamy S (2019) Travelgan: Image-to-image translation by transformation vector learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8983\u20138992","DOI":"10.1109\/CVPR.2019.00919"},{"key":"21698_CR87","doi-asserted-by":"crossref","unstructured":"Chicco D (2021) Siamese neural networks: An overview. Artif Neural Netw, pp 73\u201394","DOI":"10.1007\/978-1-0716-0826-5_3"},{"key":"21698_CR88","unstructured":"Zhao Y, Li C, Yu P, Gao J, Chen C (2020) Feature quantization improves gan training. ArXiv Preprint ArXiv:2004.02088"},{"key":"21698_CR89","doi-asserted-by":"crossref","unstructured":"Cao Y, Yao L, Pan L, Sheng Q, Chang X (2023) Guided image-to-image translation by discriminator-generator communication. IEEE Trans Multimedia","DOI":"10.1109\/TMM.2023.3282869"},{"key":"21698_CR90","doi-asserted-by":"crossref","unstructured":"Choi Y, Choi M, Kim M, Ha J, Kim S, Choo J (2018) Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8789\u20138797","DOI":"10.1109\/CVPR.2018.00916"},{"key":"21698_CR91","doi-asserted-by":"crossref","unstructured":"Choi Y, Uh Y, Yoo J, Ha J (2020) Stargan v2: Diverse image synthesis for multiple domains. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8188\u20138197","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"21698_CR92","unstructured":"Yu X, Chen Y, Liu S, Li T, Li G (2019) Multi-mapping image-to-image translation via learning disentanglement. Adv Neural Inf Proc Syst 32"},{"key":"21698_CR93","doi-asserted-by":"crossref","unstructured":"Liu R, Ge Y, Choi C, Wang X, Li H (2021) Divco: Diverse conditional image synthesis via contrastive generative adversarial network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16377\u201316386","DOI":"10.1109\/CVPR46437.2021.01611"},{"key":"21698_CR94","doi-asserted-by":"crossref","unstructured":"Mao Q, Lee H, Tseng H, Ma S, Yang M (2019) Mode seeking generative adversarial networks for diverse image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1429\u20131437","DOI":"10.1109\/CVPR.2019.00152"},{"key":"21698_CR95","doi-asserted-by":"crossref","unstructured":"Tang H, Xu D, Sebe N, Wang Y, Corso J, Yan Y (2019) Multi-channel attention selection gan with cascaded semantic guidance for cross-view image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2417\u20132426","DOI":"10.1109\/CVPR.2019.00252"},{"key":"21698_CR96","doi-asserted-by":"crossref","unstructured":"Tang H, Xu D, Sebe N, Yan Y (2019) Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation. CoRR. ArXiv Preprint ArXiv:1903.12296","DOI":"10.1109\/IJCNN.2019.8851881"},{"key":"21698_CR97","doi-asserted-by":"publisher","first-page":"1972","DOI":"10.1109\/TNNLS.2021.3105725","volume":"34","author":"H Tang","year":"2021","unstructured":"Tang H, Liu H, Xu D, Torr P, Sebe N (2021) Attentiongan: Unpaired image-to-image translation using attention-guided generative adversarial networks. IEEE Trans Neural Netw Learn Syst 34:1972\u20131987","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"21698_CR98","unstructured":"Mejjati Y, Richardt C, Tompkin J, Cosker D, Kim K (2018) Unsupervised Attention-guided Image to Image Translation"},{"key":"21698_CR99","unstructured":"Kim J (2019) U-gat-it: unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. ArXiv Preprint ArXiv:1907.10830"},{"key":"21698_CR100","doi-asserted-by":"crossref","unstructured":"Zhan F, Yu Y, Wu R, Zhang J, Cui K, Xiao A, Lu S, Miao C (2022) Bi-level feature alignment for versatile image translation and manipulation. Eur Conf Comput Vision, pp 224\u2013241","DOI":"10.1007\/978-3-031-19787-1_13"},{"key":"21698_CR101","unstructured":"Cazenavette G, De Guevara M (2021) MixerGAN: An MLP-based architecture for unpaired image-to-image translation. ArXiv Preprint ArXiv:2105.14110"},{"key":"21698_CR102","first-page":"24261","volume":"34","author":"I Tolstikhin","year":"2021","unstructured":"Tolstikhin I, Houlsby N et al (2021) Mlp-mixer: An all-mlp architecture for vision. Adv Neural Inf Process Syst 34:24261\u201324272","journal-title":"Adv Neural Inf Process Syst"},{"key":"21698_CR103","doi-asserted-by":"crossref","unstructured":"Lai X, Bai X, Hao Y (2021) Unsupervised generative adversarial networks with cross-model weight transfer mechanism for image-to-image translation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1814\u20131822","DOI":"10.1109\/ICCVW54120.2021.00208"},{"key":"21698_CR104","unstructured":"Liu M, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. Adv Neural Inf Process Syst 30"},{"key":"21698_CR105","doi-asserted-by":"crossref","unstructured":"Wu W, Cao K, Li C, Qian C, Loy C (2019) Transgaga: Geometry-aware unsupervised image-to-image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8012\u20138021","DOI":"10.1109\/CVPR.2019.00820"},{"key":"21698_CR106","first-page":"382","volume":"16","author":"K Saito","year":"2020","unstructured":"Saito K, Saenko K, Liu M (2020) Coco-funit: Few-shot unsupervised image translation with a content conditioned style encoder. Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020. Proceedings Part III 16:382\u2013398","journal-title":"Proceedings Part III"},{"key":"21698_CR107","doi-asserted-by":"publisher","first-page":"72839","DOI":"10.1109\/ACCESS.2022.3189352","volume":"10","author":"G Han","year":"2022","unstructured":"Han G, Min J, Han S (2022) EM-LAST: Effective Multidimensional Latent Space Transport for an Unpaired Image-to-Image Translation With an Energy-Based Model. IEEE Access 10:72839\u201372849","journal-title":"IEEE Access"},{"key":"21698_CR108","first-page":"3882","volume":"37","author":"J Wang","year":"2024","unstructured":"Wang J, Wang P, Liu D, Guan Q, Dianat S, Rabbani M, Rao R, Tao Z (2024) Diffusion-inspired truncated sampler for text-video retrieval. Adv Neural Inf Process Syst 37:3882\u20133906","journal-title":"Adv Neural Inf Process Syst"},{"key":"21698_CR109","unstructured":"Han C, Liang J, Wang Q, Rabbani M, Dianat S, Rao R, Wu Y, Liu D (2024) Image translation as diffusion visual programmers"},{"key":"21698_CR110","doi-asserted-by":"crossref","unstructured":"Xia B, Zhang Y, Wang S, Wang Y, Wu X, Tian Y, Yang W, Timotfe R, Van Gool L (2024) Diffi2i: Efficient diffusion model for image-to-image translation. IEEE Trans Patt Anal Mach Intell","DOI":"10.1109\/TPAMI.2024.3498003"},{"key":"21698_CR111","doi-asserted-by":"publisher","first-page":"2260","DOI":"10.3390\/rs17132260","volume":"17","author":"M Seo","year":"2025","unstructured":"Seo M, Jung J, Choi D (2025) Improved Flood Insights: Diffusion-Based SAR-to-EO Image Translation. Remote Sensing 17:2260","journal-title":"Remote Sensing"},{"key":"21698_CR112","doi-asserted-by":"crossref","unstructured":"Chen T, Hou J, Zhou Y, Xie H, Chen X, Liu Q, Guo X, Xia M, Duncan J, Liu C et al (2025) 2.5 D multi-view averaging diffusion model for 3D medical image translation: application to low-count PET reconstruction with CT-less attenuation correction. IEEE Trans Med Imaging","DOI":"10.1109\/TMI.2025.3570342"},{"key":"21698_CR113","unstructured":"Si Q, Wang B, Zhang Z (2025) Contrastive Learning Guided Latent Diffusion Model for Image-to-Image Translation. ArXiv Preprint ArXiv:2503.20484"},{"key":"21698_CR114","first-page":"30146","volume":"36","author":"D Li","year":"2023","unstructured":"Li D, Li J, Hoi S (2023) Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. Adv Neural Inf Process Syst 36:30146\u201330166","journal-title":"Adv Neural Inf Process Syst"},{"key":"21698_CR115","unstructured":"Radford A, Kim J, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et al (2021) Learning transferable visual models from natural language supervision. Int Conf Mach Learn, pp 8748\u20138763"},{"key":"21698_CR116","doi-asserted-by":"crossref","unstructured":"Kim S, Chung D (2025) Conditional brownian bridge diffusion model for vhr sar to optical image translation. IEEE Geosci Remote Sens Lett","DOI":"10.1109\/LGRS.2025.3562401"},{"key":"21698_CR117","doi-asserted-by":"crossref","unstructured":"Li B, Xue K, Liu B, Lai Y (2023) Bbdm: Image-to-image translation with brownian bridge diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1952\u20131961","DOI":"10.1109\/CVPR52729.2023.00194"},{"key":"21698_CR118","doi-asserted-by":"publisher","first-page":"697","DOI":"10.3390\/s25030697","volume":"25","author":"X Zhang","year":"2025","unstructured":"Zhang X, Zhang L, Guo H, Zheng H, Sun H, Li Y, Li R, Luan C, Tong X (2025) DCLTV: An Improved Dual-Condition Diffusion Model for Laser-Visible Image Translation. Sensors 25:697","journal-title":"Sensors"},{"key":"21698_CR119","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103747","volume":"106","author":"F Arslan","year":"2025","unstructured":"Arslan F, Kabas B, Dalmaz O, Ozbey M, \u00c7ukur T (2025) Self-consistent recursive diffusion bridge for medical image translation. Med Image Anal 106:103747","journal-title":"Med Image Anal"},{"key":"21698_CR120","doi-asserted-by":"publisher","first-page":"109501","DOI":"10.1016\/j.compbiomed.2024.109501","volume":"185","author":"S Patil","year":"2025","unstructured":"Patil S, Rajak R, Ramteke M, Rathore A (2025) MMIT-DDPM-Multilateral medical image translation with class and structure supervised diffusion-based model. Comput Biol Med 185:109501","journal-title":"Comput Biol Med"},{"key":"21698_CR121","unstructured":"Wang Z, Zheng H, He P, Chen W, Zhou M (2022) Diffusion-gan: Training gans with diffusion. ArXiv Preprint ArXiv:2206.02262"},{"key":"21698_CR122","doi-asserted-by":"crossref","unstructured":"Liu X, Zeng B, Gao S, Li S, Feng Y, Li H, Liu B, Liu J, Zhang B (2024) Ladiffgan: Training gans with diffusion supervision in latent spaces. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1115\u20131125","DOI":"10.1109\/CVPRW63382.2024.00118"},{"key":"21698_CR123","doi-asserted-by":"crossref","unstructured":"Kang M, Zhang R, Barnes C, Paris S, Kwak S, Park J, Shechtman E, Zhu J, Park T (2024) Distilling diffusion models into conditional gans. Eur Conf Comput Vision, pp 428\u2013447","DOI":"10.1007\/978-3-031-73390-1_25"},{"key":"21698_CR124","unstructured":"Kingma D, Dhariwal P (2018) Glow: Generative flow with invertible 1x1 convolutions. Adv Neural Inf Process Syst 31"},{"key":"21698_CR125","unstructured":"Simonyan K (2014) Very deep convolutional networks for large-scale image recognition. ArXiv Preprint ArXiv:1409.1556"},{"key":"21698_CR126","unstructured":"Fan W, Chen J, Liu Z (2023) Hierarchy Flow For High-Fidelity Image-to-Image Translation. ArXiv Preprint ArXiv:2308.06909"},{"key":"21698_CR127","doi-asserted-by":"crossref","unstructured":"Sun H, Mehta R, Zhou H, Huang Z, Johnson S, Prabhakaran V, Singh V (2019) Dual-glow: Conditional flow-based generative model for modality transfer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10611\u201310620","DOI":"10.1109\/ICCV.2019.01071"},{"key":"21698_CR128","unstructured":"Zheng W, Li Q, Zhang G, Wan P, Wang Z (2022) Ittr: Unpaired image-to-image translation with transformers. ArXiv Preprint ArXiv:2203.16015"},{"key":"21698_CR129","doi-asserted-by":"crossref","unstructured":"Kim S, Baek J, Park J, Kim G, Kim S (2022) InstaFormer: Instance-aware image-to-image translation with transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18321\u201318331","DOI":"10.1109\/CVPR52688.2022.01778"},{"key":"21698_CR130","doi-asserted-by":"crossref","unstructured":"Torbunov D, Huang Y, Yu H, Huang J, Yoo S, Lin M, Viren B, Ren Y (2023) Uvcgan: Unet vision transformer cycle-consistent gan for unpaired image-to-image translation. In: proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 702\u2013712","DOI":"10.1109\/WACV56688.2023.00077"},{"key":"21698_CR131","doi-asserted-by":"publisher","first-page":"2448","DOI":"10.1109\/TMI.2024.3367321","volume":"43","author":"M Chaudhary","year":"2024","unstructured":"Chaudhary M, Gerard S, Christensen G, Cooper C, Schroeder J, Hoffman E, Reinhardt J (2024) LungViT: ensembling cascade of texture sensitive hierarchical vision transformers for cross-volume chest CT image-to-image translation. IEEE Trans Med Imaging 43:2448\u20132465","journal-title":"IEEE Trans Med Imaging"},{"key":"21698_CR132","doi-asserted-by":"crossref","unstructured":"Yu Z, Wang J, Chen H, Idris M (2025) Qrs-trs: Style transfer-based image-to-image translation for carbon stock estimation in quantitative remote sensing. IEEE Access","DOI":"10.1109\/ACCESS.2025.3554045"},{"key":"21698_CR133","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2025.105177","volume":"162","author":"W Wang","year":"2025","unstructured":"Wang W, Yuan Q, Huang P, Wang X, Song H (2025) Desmoke-VCU: Improved unpaired image-to-image translation for removing smoke from laparoscopic images. Digital Signal Processing 162:105177","journal-title":"Digital Signal Processing"},{"key":"21698_CR134","doi-asserted-by":"publisher","first-page":"5546","DOI":"10.1109\/TCSVT.2024.3353932","volume":"34","author":"J Liu","year":"2024","unstructured":"Liu J, Fu H, Wang X, Ma H (2024) SwinIT: Hierarchical image-to-image translation framework without cycle consistency. IEEE Trans Circ Syst Video Technol 34:5546\u20135559","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"21698_CR135","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21698_CR136","doi-asserted-by":"crossref","unstructured":"Chen Y, Chen P, Zhou X, Lei Y, Zhou Z, Li M (2024) Implicit multi-spectral transformer: An lightweight and effective visible to infrared image translation model. In: 2024 International Joint Conference on Neural Networks (IJCNN), pp 1\u20138","DOI":"10.1109\/IJCNN60899.2024.10650029"},{"key":"21698_CR137","doi-asserted-by":"crossref","unstructured":"Chen L, Chu X, Zhang X, Sun J (2022) Simple baselines for image restoration. Eur Conf Comput Vision, pp 17\u201333","DOI":"10.1007\/978-3-031-20071-7_2"},{"key":"21698_CR138","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1007\/s11263-023-01866-y","volume":"132","author":"S Kim","year":"2024","unstructured":"Kim S, Baek J, Park J, Ha E, Jung H, Lee T, Kim S (2024) Instaformer++: Multi-domain instance-aware image-to-image translation with transformer. Int J Comput Vision 132:1167\u20131186","journal-title":"Int J Comput Vision"},{"key":"21698_CR139","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.109062","volume":"113","author":"Z Zheng","year":"2026","unstructured":"Zheng Z, Fan C, Wang C, Wang M, He X, He X (2026) A GAN integrating CNN and transformer with mutual information and grayscale-based loss functions for modality translation in medical image. Biomedical Signal Processing And Control 113:109062","journal-title":"Biomedical Signal Processing And Control"},{"key":"21698_CR140","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"21698_CR141","doi-asserted-by":"crossref","unstructured":"Zhou B, Zhao H, Puig X, Fidler S, Barriuso A, Torralba A (2017) Scene parsing through ade20k dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 633\u2013641","DOI":"10.1109\/CVPR.2017.544"},{"key":"21698_CR142","doi-asserted-by":"crossref","unstructured":"Milford M, Wyeth G (2012) SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights. In: 2012 IEEE international conference on robotics and automation, pp 1643\u20131649","DOI":"10.1109\/ICRA.2012.6224623"},{"key":"21698_CR143","unstructured":"Yu F, Xian W, Chen Y, Liu F, Liao M, Madhavan V, Darrell T (2018) Bdd100k: a diverse driving video database with scalable annotation tooling. ArXiv Preprint ArXiv:1805.04687"},{"key":"21698_CR144","doi-asserted-by":"crossref","unstructured":"Liu Z, Luo P, Wang X, Tang X (2015) Deep learning face attributes in the wild. In: Proceedings of the IEEE international conference on computer vision, pp 3730\u20133738","DOI":"10.1109\/ICCV.2015.425"},{"key":"21698_CR145","doi-asserted-by":"crossref","unstructured":"Liu Z, Luo P, Qiu S, Wang X, Tang X (2016) Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1096\u20131104","DOI":"10.1109\/CVPR.2016.124"},{"key":"21698_CR146","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1007\/s00138-018-0922-2","volume":"29","author":"O Poursaeed","year":"2018","unstructured":"Poursaeed O, Matera T, Belongie S (2018) Vision-based real estate price estimation. Mach Vision Appl 29:667\u2013676","journal-title":"Mach Vision Appl"},{"key":"21698_CR147","doi-asserted-by":"crossref","unstructured":"Tyle\u010dek R, \u0160\u00e1ra R (2013) Spatial pattern templates for recognition of objects with regular structure. Pattern Recognition: 35th German Conference, GCPR 2013, Saarbr\u00fccken, Germany, September 3-6, 2013. Proceedings 35, pp 364\u2013374","DOI":"10.1007\/978-3-642-40602-7_39"},{"key":"21698_CR148","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4401\u20134410","DOI":"10.1109\/CVPR.2019.00453"},{"key":"21698_CR149","doi-asserted-by":"crossref","unstructured":"Plummer B, Wang L, Cervantes C, Caicedo J, Hockenmaier J, Lazebnik S (2015) Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE international conference on computer vision, pp 2641\u20132649","DOI":"10.1109\/ICCV.2015.303"},{"key":"21698_CR150","first-page":"102","volume":"14","author":"S Richter","year":"2016","unstructured":"Richter S, Vineet V, Roth S, Koltun V (2016) Playing for data: Ground truth from computer games. Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016. Proceedings Part II 14:102\u2013118","journal-title":"Proceedings Part II"},{"key":"21698_CR151","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"21698_CR152","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE conference on computer vision and pattern recognition, pp 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"21698_CR153","first-page":"746","volume":"12","author":"N Silberman","year":"2012","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from rgbd images. Computer Vision-ECCV 2012: 12th European Conference On Computer Vision, Florence, Italy, October 7\u201313, 2012. Proceedings Part V 12:746\u2013760","journal-title":"Proceedings Part V"},{"key":"21698_CR154","unstructured":"Cao Z, Hidalgo G, Simon T, Wei S, Sheikh Y (2018) Openpose: realtime multi-person 2d pose estimation using part affinity fields 6:1812. ArXiv Preprint ArXiv:1812.08008"},{"key":"21698_CR155","doi-asserted-by":"crossref","unstructured":"Bi S, Sunkavalli K, Perazzi F, Shechtman E, Kim V, Ramamoorthi R (2019) Deep cg2real: Synthetic-to-real translation via image disentanglement. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2730\u20132739","DOI":"10.1109\/ICCV.2019.00282"},{"key":"21698_CR156","doi-asserted-by":"crossref","unstructured":"Yu A, Grauman K (2014) Fine-grained visual comparisons with local learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 192\u2013199","DOI":"10.1109\/CVPR.2014.32"},{"key":"21698_CR157","doi-asserted-by":"crossref","unstructured":"Kalkowski S, Schulze C, Dengel A, Borth D (2015) Real-time analysis and visualization of the yfcc100m dataset. In: Proceedings of the 2015 workshop on community-organized multimodal mining: opportunities for novel solutions, pp 25\u201330","DOI":"10.1145\/2814815.2814820"},{"key":"21698_CR158","unstructured":"Ozaydin B, Zhang T, S\u00fcsstrunk S, Salzmann M (2022) DSI2I: Dense Style for Unpaired Image-to-Image Translation. ArXiv Preprint ArXiv:2212.13253"},{"key":"21698_CR159","unstructured":"Zhao Y, Li C, Yu P, Gao J, Chen C (2020) Feature quantization improves GAN training. ArXiv Preprint ArXiv:2004.02088"},{"key":"21698_CR160","doi-asserted-by":"publisher","first-page":"6858","DOI":"10.3390\/s23156858","volume":"23","author":"H Lee","year":"2023","unstructured":"Lee H, Li Y, Lee T, Aslam M (2023) Progressively unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. Sensors 23:6858","journal-title":"Sensors"},{"key":"21698_CR161","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/TPAMI.2019.2950198","volume":"43","author":"J Lin","year":"2019","unstructured":"Lin J, Chen Z, Xia Y, Liu S, Qin T, Luo J (2019) Exploring explicit domain supervision for latent space disentanglement in unpaired image-to-image translation. IEEE Trans Patt Anal Mach Intell 43:1254\u20131266","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"21698_CR162","first-page":"155","volume":"16","author":"Z Zheng","year":"2020","unstructured":"Zheng Z, Wu Y, Han X, Shi J (2020) Forkgan: Seeing into the rainy night. Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020. Proceedings Part III 16:155\u2013170","journal-title":"Proceedings Part III"},{"key":"21698_CR163","doi-asserted-by":"crossref","unstructured":"Cao J, Huang H, Li Y, He R, Sun Z (2020) Informative sample mining network for multi-domain image-to-image translation. Eur Conf Comput Vision, pp 404\u2013419","DOI":"10.1007\/978-3-030-58529-7_24"},{"key":"21698_CR164","unstructured":"Katzir O, Lischinski D, Cohen-Or D (2019) Cross-domain cascaded deep feature translation. ArXiv Preprint ArXiv:1906.01526"},{"key":"21698_CR165","doi-asserted-by":"crossref","unstructured":"Shubhra Ghosh S, Hua Y, Subhra Mukherjee S, Robertson N (2018) IEGAN: Multi-purpose Perceptual Quality Image Enhancement Using Generative Adversarial Network. ArXiv Preprint ArXiv:1811.09134","DOI":"10.1109\/WACV.2019.00009"},{"key":"21698_CR166","unstructured":"Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X (2016) Improved techniques for training gans. Adv Neural Inf Process Syst 29"},{"key":"21698_CR167","unstructured":"Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv Neural Inf Process Syst 30"},{"key":"21698_CR168","doi-asserted-by":"crossref","unstructured":"Shaham T, Dekel T, Michaeli T (2019) Singan: Learning a generative model from a single natural image. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4570\u20134580","DOI":"10.1109\/ICCV.2019.00467"},{"key":"21698_CR169","unstructured":"Bi\u0144kowski M, Sutherland D, Arbel M, Gretton A (2018) Demystifying mmd gans. ArXiv Preprint ArXiv:1801.01401"},{"key":"21698_CR170","doi-asserted-by":"crossref","unstructured":"Lin Y, Wang Y, Li Y, Gao Y, Wang Z, Khan L (2021) Attention-based spatial guidance for image-to-image translation. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 816\u2013825","DOI":"10.1109\/WACV48630.2021.00086"},{"key":"21698_CR171","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros A, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 586\u2013595","DOI":"10.1109\/CVPR.2018.00068"},{"key":"21698_CR172","unstructured":"Richardson E, Weiss Y (2018) On GANs and GMMs. Adv Neural Inf Process Syst 31"},{"key":"21698_CR173","doi-asserted-by":"crossref","unstructured":"Su S, Song J, Gao L, Zhu J (2021) Towards unsupervised deformable-instances image-to-image translation. IJCAI, pp 1004\u20131010","DOI":"10.24963\/ijcai.2021\/139"},{"key":"21698_CR174","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik A, Sheikh H, Simoncelli E (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600\u2013612","journal-title":"IEEE Trans Image Process"},{"key":"21698_CR175","unstructured":"Korotin A, Selikhanovych D, Burnaev E (2023) Neural Optimal Transport"},{"key":"21698_CR176","doi-asserted-by":"crossref","unstructured":"Zhang P, Zhang B, Chen D, Yuan L, Wen F (2020) Cross-domain correspondence learning for exemplar-based image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5143\u20135153","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"21698_CR177","doi-asserted-by":"crossref","unstructured":"Zhao Y, Chen C (2021) Unpaired image-to-image translation via latent energy transport. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16418\u201316427","DOI":"10.1109\/CVPR46437.2021.01615"},{"key":"21698_CR178","doi-asserted-by":"publisher","first-page":"3178","DOI":"10.3390\/math12203178","volume":"12","author":"H Tu","year":"2024","unstructured":"Tu H, Wang Z, Zhao Y (2024) Unpaired image-to-image translation with diffusion adversarial network. Mathematics 12:3178","journal-title":"Mathematics"},{"key":"21698_CR179","unstructured":"Vivekananthan S (2024) Comparative analysis of generative models: Enhancing image synthesis with vaes, gans, and stable diffusion. ArXiv Preprint ArXiv:2408.08751"},{"key":"21698_CR180","doi-asserted-by":"publisher","first-page":"252","DOI":"10.3390\/jimaging11080252","volume":"11","author":"Z Sordo","year":"2025","unstructured":"Sordo Z, Chagnon E, Hu Z, Donatelli J, Andeer P, Nico P, Northen T, Ushizima D (2025) Synthetic scientific image generation with VAE, GAN, and diffusion model architectures. J Imaging 11:252","journal-title":"J Imaging"},{"key":"21698_CR181","unstructured":"Wu Y, Liao F, Chen M, Ho P, Nabiei F, Shiu D (2025) Latent Flow Transformer. ArXiv Preprint ArXiv:2505.14513"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21698-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21698-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21698-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T06:03:44Z","timestamp":1779084224000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21698-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":181,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["21698"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21698-5","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]},"assertion":[{"value":"9 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We do not have any conflict of interest related to the manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"All authors consent to the publication of this manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Publish"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"527"}}