{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:12:09Z","timestamp":1783768329788,"version":"3.55.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42276187"],"award-info":[{"award-number":["42276187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02334-6","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:17:57Z","timestamp":1778048277000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sonar images generation method based on improved stable diffusion combined with ControlNet model"],"prefix":"10.1007","volume":"32","author":[{"given":"Jier","family":"Xi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiufen","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuxiang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunying","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanjie","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"2334_CR1","doi-asserted-by":"crossref","unstructured":"Elmezain, M., Saoud, L.S., Sultan, A., Heshmat, M., Seneviratne, L., Hussain, I.: Advancing underwater vision: a survey of deep learning models for underwater object recognition and tracking. IEEE Access (2025)","DOI":"10.1109\/ACCESS.2025.3534098"},{"issue":"1","key":"2334_CR2","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s44295-024-00023-6","volume":"2","author":"M Jian","year":"2024","unstructured":"Jian, M., Yang, N., Tao, C., Zhi, H., Luo, H.: Underwater object detection and datasets: a survey. Intell. Marine Technol. Syst. 2(1), 9 (2024)","journal-title":"Intelligent Marine Technology and Systems"},{"issue":"3","key":"2334_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3759243","volume":"58","author":"L Chen","year":"2025","unstructured":"Chen, L., Huang, Y., Dong, J., Xu, Q., Kwong, S., Lu, H., Lu, H., Li, C.: Underwater optical object detection in the era of artificial intelligence: Current, challenge, and future. ACM Comput. Surv. 58(3), 1\u201334 (2025)","journal-title":"ACM Comput. Surv."},{"key":"2334_CR4","first-page":"1","volume":"72","author":"J Fan","year":"2023","unstructured":"Fan, J., Wang, X., Zhou, C., Ou, Y., Jing, F., Hou, Z.: Development, calibration, and image processing of underwater structured light vision system: A survey. IEEE Trans. Instrum. Meas. 72, 1\u201318 (2023)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"21","key":"2334_CR5","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.ifacol.2019.12.322","volume":"52","author":"M Sung","year":"2019","unstructured":"Sung, M., Kim, J., Kim, J., Yu, S.-C.: Realistic sonar image simulation using generative adversarial network. IFAC-Papers OnLine 52(21), 291\u2013296 (2019)","journal-title":"IFAC-PapersOnLine"},{"issue":"9","key":"2334_CR6","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/LGRS.2020.3005679","volume":"18","author":"Y Jiang","year":"2020","unstructured":"Jiang, Y., Ku, B., Kim, W., Ko, H.: Side-scan sonar image synthesis based on generative adversarial network for images in multiple frequencies. IEEE Geosci. Remote Sens. Lett. 18(9), 1505\u20131509 (2020)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"2334_CR7","doi-asserted-by":"crossref","unstructured":"Bai, Z., Xu, H., Ding, Q., Zhang, X.: Side-scan sonar image classification with zero-shot and style transfer. IEEE Trans. Instrum. Meas. (2024)","DOI":"10.1109\/TIM.2024.3352693"},{"issue":"2","key":"2334_CR8","doi-asserted-by":"publisher","first-page":"352","DOI":"10.3390\/jmse12020352","volume":"12","author":"J Xi","year":"2024","unstructured":"Xi, J., Ye, X.: Sonar image target detection based on simulated stain-like noise and shadow enhancement in optical images under zero-shot learning. J. Marine Sci. Eng. 12(2), 352 (2024)","journal-title":"Journal of Marine Science and Engineering"},{"key":"2334_CR9","first-page":"229","volume":"4","author":"K Sivachandra","year":"2024","unstructured":"Sivachandra, K., Kumudham, R.: A review: Object detection and classification using side scan sonar images via deep learning techniques. Mod. Approaches in Mach. Learn. Cogn. Sci. : A Walkthrough 4, 229\u2013249 (2024)","journal-title":"Modern Approaches in Machine Learning and Cognitive Science: A Walkthrough"},{"issue":"15","key":"2334_CR10","doi-asserted-by":"publisher","first-page":"1823","DOI":"10.3390\/electronics10151823","volume":"10","author":"Q Ge","year":"2021","unstructured":"Ge, Q., Ruan, F., Qiao, B., Zhang, Q., Zuo, X., Dang, L.: Side-scan sonar image classification based on style transfer and pre-trained convolutional neural networks. Electron. 10(15), 1823 (2021)","journal-title":"Electronics"},{"key":"2334_CR11","first-page":"1","volume":"60","author":"C Huang","year":"2021","unstructured":"Huang, C., Zhao, J., Yu, Y., Zhang, H.: Comprehensive sample augmentation by fully considering sss imaging mechanism and environment for shipwreck detection under zero real samples. IEEE Trans. Geosci. Remote Sens. 60, 1\u201314 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2334_CR12","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhao, J., Yu, Y., Huang, C.: A sample augmentation method for side-scan sonar full-class images that can be used for detection and segmentation. IEEE Trans. Geosci. Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3371051"},{"issue":"6","key":"2334_CR13","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.3390\/jmse11061103","volume":"11","author":"Z Yang","year":"2023","unstructured":"Yang, Z., Zhao, J., Zhang, H., Yu, Y., Huang, C.: A side-scan sonar image synthesis method based on a diffusion model. J. Marine Sci. Eng. 11(6), 1103 (2023)","journal-title":"Journal of Marine Science and Engineering"},{"key":"2334_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102846","volume":"88","author":"A Kazerouni","year":"2023","unstructured":"Kazerouni, A., Aghdam, E.K., Heidari, M., Azad, R., Fayyaz, M., Hacihaliloglu, I., Merhof, D.: Diffusion models in medical imaging: A comprehensive survey. Med. Image Anal. 88, 102846 (2023)","journal-title":"Med. Image Anal."},{"key":"2334_CR15","first-page":"21696","volume":"34","author":"D Kingma","year":"2021","unstructured":"Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. Adv. Neural. Inf. Process. Syst. 34, 21696\u201321707 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2334_CR16","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2334_CR17","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"2334_CR18","unstructured":"Yu, Y., Zhang, W., Deng, Y.: Frechet inception distance (fid) for evaluating gans. China Univ. Min. Technol. Beijing Graduate Sch. 3 (2021)"},{"key":"2334_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conf. Comput. Vis. Pattern Recognit, pp. 586\u2013595. (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"issue":"11","key":"2334_CR20","doi-asserted-by":"publisher","first-page":"2385","DOI":"10.1109\/TIP.2009.2025923","volume":"18","author":"MP Sampat","year":"2009","unstructured":"Sampat, M.P., Wang, Z., Gupta, S., Bovik, A.C., Markey, M.K.: Complex wavelet structural similarity: A new image similarity index. IEEE Trans. Image Process. 18(11), 2385\u20132401 (2009)","journal-title":"IEEE Trans. Image Process."},{"key":"2334_CR21","doi-asserted-by":"crossref","unstructured":"Petrov, E., Kharina, N.: Markov processes in image processing. In: J. Phys: Conf. Ser., vol. 1015, p. 032059 (2018). IOP Publishing","DOI":"10.1088\/1742-6596\/1015\/3\/032059"},{"key":"2334_CR22","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., pp. 10684\u201310695. (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2334_CR23","doi-asserted-by":"crossref","unstructured":"Singh, D., Valdenegro-Toro, M.: The marine debris dataset for forward-looking sonar semantic segmentation. In: Proceedings of the Ieee\/cvf Int. Conf. Comput. Vis., pp. 3741\u20133749. (2021)","DOI":"10.1109\/ICCVW54120.2021.00417"},{"key":"2334_CR24","unstructured":"Xu, Y., He, Z., Shan, S., Chen, X.: Ctrlora: An extensible and efficient framework for controllable image generation. arXiv preprint arXiv:2410.09400 (2024)"},{"key":"2334_CR25","doi-asserted-by":"crossref","unstructured":"Li, F., Wu, H., Zhang, J.: Lightweight diffusion model for synthesizing malicious network traffic. In: NAECON 2024-IEEE Nat. Aerosp. and Electron. Conf., pp. 409\u2013413. (2024). IEEE","DOI":"10.1109\/NAECON61878.2024.10670640"},{"key":"2334_CR26","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"issue":"1","key":"2334_CR27","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1038\/s43586-024-00363-x","volume":"4","author":"J Healy","year":"2024","unstructured":"Healy, J., McInnes, L.: Uniform manifold approximation and projection. Nature Reviews Methods Primers 4(1), 82 (2024)","journal-title":"Nature Reviews Methods Primers"},{"key":"2334_CR28","unstructured":"Maaten, L., Hinton, G.: Visualizing data using t-sne. Journal of machine learning research 9(11) (2008)"},{"key":"2334_CR29","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"2334_CR30","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conf. Comput. Vis. Pattern Recognit., pp. 3213\u20133223. (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"2334_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107691","volume":"173","author":"C Li","year":"2021","unstructured":"Li, C., Ye, X., Cao, D., Hou, J., Yang, H.: Zero shot objects classification method of side scan sonar image based on synthesis of pseudo samples. Appl. Acoust. 173, 107691 (2021)","journal-title":"Appl. Acoust."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02334-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02334-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02334-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:19:38Z","timestamp":1783765178000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02334-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2334"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02334-6","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"13 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"301"}}