{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:26:53Z","timestamp":1783423613872,"version":"3.54.6"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051264","type":"print"},{"value":"9783032051271","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-05127-1_50","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:16:17Z","timestamp":1758316577000},"page":"521-531","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["SurgSora: Object-Aware Diffusion Model for\u00a0Controllable Surgical Video Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4312-7151","authenticated-orcid":false,"given":"Tong","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuya","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9762-6821","authenticated-orcid":false,"given":"Long","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6488-1551","authenticated-orcid":false,"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6406-2505","authenticated-orcid":false,"given":"Luping","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"50_CR1","unstructured":"Barratt, S., Sharma, R.: A note on the inception score. arXiv preprint arXiv:1801.01973 (2018)"},{"key":"50_CR2","unstructured":"Cho, J., et al.: Surgen: text-guided diffusion model for surgical video generation. arXiv preprint arXiv:2408.14028 (2024)"},{"issue":"3","key":"50_CR3","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1177\/02783649231209338","volume":"43","author":"H Gao","year":"2024","unstructured":"Gao, H., et al.: Transendoscopic flexible parallel continuum robotic mechanism for bimanual endoscopic submucosal dissection. Inter. J. Robot. Re. 43(3), 281\u2013304 (2024)","journal-title":"Inter. J. Robot. Re."},{"key":"50_CR4","doi-asserted-by":"crossref","unstructured":"Ge, S., Mahapatra, A., Parmar, G., Zhu, J.Y., Huang, J.B.: On the content bias in fr\u00e9chet video distance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00695"},{"key":"50_CR5","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in Neural Inform. Process. Syst. 30 (2017)"},{"issue":"13","key":"50_CR6","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1049\/el:20080522","volume":"44","author":"Q Huynh-Thu","year":"2008","unstructured":"Huynh-Thu, Q., Ghanbari, M.: Scope of validity of psnr in image\/video quality assessment. Electron. Lett. 44(13), 800\u2013801 (2008)","journal-title":"Electron. Lett."},{"key":"50_CR7","doi-asserted-by":"publisher","unstructured":"Iliash, I., Allmendinger, S., Meissen, F., K\u00fchl, N., R\u00fcckert, D.: Interactive generation of laparoscopic videos with diffusion models. In: MICCAI Workshop on Deep Generative Models. pp. 109\u2013118. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-72744-3_11","DOI":"10.1007\/978-3-031-72744-3_11"},{"key":"50_CR8","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"50_CR9","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: Endora: video generation models as endoscopy simulators. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 230\u2013240. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-72089-5_22","DOI":"10.1007\/978-3-031-72089-5_22"},{"key":"50_CR10","doi-asserted-by":"crossref","unstructured":"Li, Y., Min, M., Shen, D., Carlson, D., Carin, L.: Video generation from text. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"50_CR11","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"50_CR12","doi-asserted-by":"crossref","unstructured":"Niu, M., Cun, X., Wang, X., Zhang, Y., Shan, Y., Zheng, Y.: Mofa-video: Controllable image animation via generative motion field adaptions in frozen image-to-video diffusion model. arXiv preprint arXiv:2405.20222 (2024)","DOI":"10.1007\/978-3-031-72655-2_7"},{"key":"50_CR13","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., et al.: Surgical text-to-image generation. Pattern Recogn. Lett. (2025)","DOI":"10.1016\/j.patrec.2025.02.002"},{"key":"50_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102433","volume":"78","author":"CI Nwoye","year":"2022","unstructured":"Nwoye, C.I., et al.: Rendezvous: attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Med. Image Anal. 78, 102433 (2022)","journal-title":"Med. Image Anal."},{"issue":"3","key":"50_CR15","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1080\/21681163.2020.1835560","volume":"9","author":"T Ozawa","year":"2021","unstructured":"Ozawa, T., et al.: Synthetic laparoscopic video generation for machine learning-based surgical instrument segmentation from real laparoscopic video and virtual surgical instruments. Comput. Methods Biomech. Biomed. Eng. Imaging Visualizat. 9(3), 225\u2013232 (2021)","journal-title":"Comput. Methods Biomech. Biomed. Eng. Imaging Visualizat."},{"key":"50_CR16","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"50_CR17","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 Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"50_CR18","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Tulyakov, S., Elhoseiny, M.: Stylegan-v: a continuous video generator with the price, image quality and perks of stylegan2. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3626\u20133636 (2022)","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"50_CR19","unstructured":"Sun, W., et al.: Bora: biomedical generalist video generation model. arXiv preprint arXiv:2407.08944 (2024)"},{"key":"50_CR20","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"50_CR21","unstructured":"Wang, G., et al.: Copesd: a multi-level surgical motion dataset for training large vision-language models to co-pilot endoscopic submucosal dissection. arXiv preprint arXiv:2410.07540 (2024)"},{"issue":"9","key":"50_CR22","first-page":"1","volume":"56","author":"S Wang","year":"2024","unstructured":"Wang, S., Du, Y., Guo, X., Pan, B., Qin, Z., Zhao, L.: Controllable data generation by deep learning: a review. ACM Comput. Surv. 56(9), 1\u201338 (2024)","journal-title":"ACM Comput. Surv."},{"key":"50_CR23","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: A recipe for scaling up text-to-video generation with text-free videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6572\u20136582 (2024)","DOI":"10.1109\/CVPR52733.2024.00628"},{"key":"50_CR24","unstructured":"Wang, Z., Zhang, L., Wang, L., Zhu, M., Zhang, Z.: Optical flow representation alignment mamba diffusion model for medical video generation. arXiv preprint arXiv:2411.01647 (2024)"},{"issue":"4","key":"50_CR25","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.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"50_CR26","unstructured":"Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., Zhao, H.: Depth anything v2. arXiv preprint arXiv:2406.09414 (2024)"},{"key":"50_CR27","doi-asserted-by":"publisher","unstructured":"Yeganeh, Y., et al.: Visage: video synthesis using action graphs for surgery. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 146\u2013156. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-77610-6_14","DOI":"10.1007\/978-3-031-77610-6_14"},{"key":"50_CR28","unstructured":"Yu, S., et al.: Generating videos with dynamics-aware implicit generative adversarial networks. In: International Conference on Learning Representations (2022)"},{"key":"50_CR29","doi-asserted-by":"crossref","unstructured":"Zhan, X., Pan, X., Liu, Z., Lin, D., Loy, C.C.: Self-supervised learning via conditional motion propagation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1881\u20131889 (2019)","DOI":"10.1109\/CVPR.2019.00198"},{"key":"50_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05127-1_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:16:26Z","timestamp":1758316586000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05127-1_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051264","9783032051271"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05127-1_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}