{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T02:24:08Z","timestamp":1779416648916,"version":"3.53.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["90696704"],"award-info":[{"award-number":["90696704"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018707","name":"HORIZON EUROPE Reforming and enhancing the European Research and Innovation system","doi-asserted-by":"publisher","award":["101092646"],"award-info":[{"award-number":["101092646"]}],"id":[{"id":"10.13039\/100018707","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>\n                      <jats:bold>Purpose<\/jats:bold>\n                    <\/jats:title>\n                    <jats:p>Estimating the 6 degrees of freedom (DoF) pose of an endoscope is crucial for various applications in minimally invasive computer-assisted surgery. Image-based approaches are some of the most practical solutions for pose estimation in surgical environments, due to a limited workspace and sensor constraints. However, these methods often struggle or fail in dynamic scenes, such as those involving tissue deformation, surgical tool movement, and tool-tissue interaction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>\n                      <jats:bold>Methods<\/jats:bold>\n                    <\/jats:title>\n                    <jats:p>We propose DyEndoVO, an end-to-end visual odometry method in dynamic endoscopic scenes. Our method consists of a transformer-based motion detection network and a weighted pose-optimization module. The motion detection network infers scene dynamics and guides the pose estimation. Furthermore, we introduce a semi-synthetic dataset featuring tissue and tool movement categories. It serves as training data, improving pose estimation accuracy, and also includes motion masks to enable a fine-grained inspection and evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>\n                      <jats:bold>Results<\/jats:bold>\n                    <\/jats:title>\n                    <jats:p>DyEndoVO significantly outperforms state-of-the-art methods in pose estimation for dynamic surgical scenes. Despite being trained solely on a synthetic dataset, our method generalizes well to real-world data without fine-tuning. Further analysis attributes this success to the effective detection of scene dynamics and the adaptation in the learned weight toward pose estimation; moreover, the semi-synthetic dataset also plays a key role in bridging the sim-to-real gap.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>\n                      <jats:bold>Conclusions<\/jats:bold>\n                    <\/jats:title>\n                    <jats:p>In this work, we aim to improve the accuracy and robustness of pose estimation in challenging dynamic surgical scenes, by effectively handling scene dynamics. Our method, combined with the proposed synthetic dataset, demonstrates improved performance in pose estimation and generalizes well to real-world data, showing its potential in advancing related works such as SLAM and 3D reconstruction in complex surgical environments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-025-03549-0","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T06:19:29Z","timestamp":1766384369000},"page":"723-733","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DyEndoVO: scene dynamics-aware pose estimation of endoscope in minimally invasive surgery"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7943-7986","authenticated-orcid":false,"given":"Jinjing","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reuben","family":"Docea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Micha","family":"Pfeiffer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Wagner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marius","family":"Distler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefanie","family":"Speidel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,22]]},"reference":[{"issue":"6","key":"3549_CR1","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos C, Elvira R, Rodr\u00edguez JJG, Montiel JM, Tard\u00f3s JD (2021) ORB-SLAM3: An accurate open-source library for visual, visual-inertial, and multimap SLAM. IEEE Trans Rob 37(6):1874\u20131890","journal-title":"IEEE Trans Rob"},{"key":"3549_CR2","doi-asserted-by":"crossref","unstructured":"Whelan T, Leutenegger S, Salas-Moreno RF, Glocker B, Davison AJ (2015) ElasticFusion: Dense SLAM without a pose graph. In: Robotics: Science and Systems (RSS), vol 11. Rome","DOI":"10.15607\/RSS.2015.XI.001"},{"key":"3549_CR3","doi-asserted-by":"publisher","first-page":"28023","DOI":"10.52202\/068431-2032","volume":"35","author":"J Xie","year":"2022","unstructured":"Xie J, Xie W, Zisserman A (2022) Segmenting moving objects via an object-centric layered representation. Adv Neural Inform Process Sys 35:28023\u201328036","journal-title":"Adv Neural Inform Process Sys"},{"key":"3549_CR4","doi-asserted-by":"crossref","unstructured":"Hayoz M, Hahne C, Gallardo M, Candinas D, Kurmann T, Allan M, Sznitman R (2023) Learning how to robustly estimate camera pose in endoscopic videos. Int J Computer Assist Radiol Surg, 1\u20138","DOI":"10.1007\/s11548-023-02919-w"},{"key":"3549_CR5","doi-asserted-by":"crossref","unstructured":"Kendall A, Grimes M, Cipolla R (2015) Posenet: A convolutional network for real-time 6-dof camera relocalization. In: Proc IEEE Int Conf Computer Vision (ICCV), pp 2938\u20132946","DOI":"10.1109\/ICCV.2015.336"},{"key":"3549_CR6","doi-asserted-by":"crossref","unstructured":"Laskar Z, Melekhov I, Kalia S, Kannala J (2017) Camera relocalization by computing pairwise relative poses using convolutional neural network. In: Proceedings of the IEEE Int Conf Computer Vision (ICCV) Workshops, pp 929\u2013938","DOI":"10.1109\/ICCVW.2017.113"},{"key":"3549_CR7","doi-asserted-by":"crossref","unstructured":"Ding M, Wang Z, Sun J, Shi J, Luo P (2019) CamNet: Coarse-to-fine retrieval for camera re-localization. In: Proc IEEE\/CVF Int Conf Computer Vision (ICCV), pp 2871\u20132880","DOI":"10.1109\/ICCV.2019.00296"},{"key":"3549_CR8","doi-asserted-by":"crossref","unstructured":"Engel J, Sch\u00f6ps T, Cremers D (2014) LSD-SLAM: Large-scale direct monocular SLAM. In: European Conference on Computer Vision (ECCV), pp. 834\u2013849. Springer","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"3549_CR9","doi-asserted-by":"crossref","unstructured":"Parameshwara CM, Hari G, Ferm\u00fcller C, Sanket NJ, Aloimonos Y (2022) Diffposenet: Direct differentiable camera pose estimation. In: Proc IEEE\/CVF Conf Computer Vision Pattern Recogn (CVPR), pp 6845\u20136854","DOI":"10.1109\/CVPR52688.2022.00672"},{"key":"3549_CR10","doi-asserted-by":"crossref","unstructured":"Campbell D, Liu L, Gould S (2020) Solving the blind perspective-n-point problem end-to-end with robust differentiable geometric optimization. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16, pp. 244\u2013261. Springer","DOI":"10.1007\/978-3-030-58536-5_15"},{"issue":"8","key":"3549_CR11","first-page":"3988","volume":"44","author":"S Gould","year":"2021","unstructured":"Gould S, Hartley R, Campbell D (2021) Deep declarative networks. IEEE Trans Pattern Anal Mach Intell 44(8):3988\u20134004","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3549_CR12","doi-asserted-by":"crossref","unstructured":"Brachmann E, Krull A, Nowozin S, Shotton J, Michel F, Gumhold S, Rother C (2017) DSAC: Differentiable RANSAC for camera localization. In: Proc IEEE Conf Computer Vision Pattern Recogn (CVPR), pp 6684\u20136692","DOI":"10.1109\/CVPR.2017.267"},{"key":"3549_CR13","first-page":"16558","volume":"34","author":"Z Teed","year":"2021","unstructured":"Teed Z, Deng J (2021) Droid-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras. Adv Neural Inform Process Sys 34:16558\u201316569","journal-title":"Adv Neural Inform Process Sys"},{"key":"3549_CR14","first-page":"39033","volume":"36","author":"Z Teed","year":"2023","unstructured":"Teed Z, Lipson L, Deng J (2023) Deep patch visual odometry. Adv Neural Inform Process Syst 36:39033\u201339051","journal-title":"Adv Neural Inform Process Syst"},{"key":"3549_CR15","doi-asserted-by":"crossref","unstructured":"Zhong F, Wang S, Zhang Z, Wang Y (2018) Detect-SLAM: Making object detection and SLAM mutually beneficial. In: 2018 IEEE Winter Conf Appl Computer Vision (WACV), pp 1001\u20131010. IEEE","DOI":"10.1109\/WACV.2018.00115"},{"issue":"4","key":"3549_CR16","doi-asserted-by":"publisher","first-page":"4076","DOI":"10.1109\/LRA.2018.2860039","volume":"3","author":"B Bescos","year":"2018","unstructured":"Bescos B, F\u00e1cil JM, Civera J, Neira J (2018) DynaSLAM: Tracking, mapping, and inpainting in dynamic scenes. IEEE Robot Autom Lett 3(4):4076\u2013483","journal-title":"IEEE Robot Autom Lett"},{"key":"3549_CR17","doi-asserted-by":"crossref","unstructured":"Yu C, Liu Z, Liu X-J, Xie F, Yang Y, Wei Q, Fei Q (2018) DS-SLAM: A semantic visual SLAM towards dynamic environments. In: 2018 IEEE\/RSJ Int Conf Intell Robots Syst (IROS), pp 1168\u20131174. IEEE","DOI":"10.1109\/IROS.2018.8593691"},{"key":"3549_CR18","doi-asserted-by":"crossref","unstructured":"Zhang T, Zhang H, Li Y, Nakamura Y, Zhang L (2020) Flowfusion: Dynamic dense RGB-D SLAM based on optical flow. In: 2020 IEEE Int Conf Robot Autom (ICRA), pp 7322\u20137328. IEEE","DOI":"10.1109\/ICRA40945.2020.9197349"},{"issue":"2","key":"3549_CR19","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1109\/LRA.2019.2892199","volume":"4","author":"A Marmol","year":"2019","unstructured":"Marmol A, Banach A, Peynot T (2019) Dense-ArthroSLAM: Dense intra-articular 3-d reconstruction with robust localization prior for arthroscopy. IEEE Robot Autom Lett 4(2):918\u2013925","journal-title":"IEEE Robot Autom Lett"},{"issue":"1","key":"3549_CR20","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1109\/TMI.2013.2282997","volume":"33","author":"OG Grasa","year":"2013","unstructured":"Grasa OG, Bernal E, Casado S, Gil I, Montiel J (2013) Visual SLAM for handheld monocular endoscope. IEEE Trans Med Imag 33(1):135\u2013146","journal-title":"IEEE Trans Med Imag"},{"issue":"1","key":"3549_CR21","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1109\/TMI.2018.2856109","volume":"38","author":"N Mahmoud","year":"2018","unstructured":"Mahmoud N, Collins T, Hostettler A, Soler L, Doignon C, Montiel JMM (2018) Live tracking and dense reconstruction for handheld monocular endoscopy. IEEE Trans Med Imag 38(1):79\u201389","journal-title":"IEEE Trans Med Imag"},{"issue":"5","key":"3549_CR22","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1007\/s11548-023-03055-1","volume":"19","author":"J Song","year":"2024","unstructured":"Song J, Zhang R, Zhu Q, Lin J, Ghaffari M (2024) BDIS-SLAM: A lightweight CPU-based dense stereo SLAM for surgery. Int J Comput Assist Radiol Surg 19(5):811\u2013820","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"1","key":"3549_CR23","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/TRO.2020.3020739","volume":"37","author":"J Lamarca","year":"2020","unstructured":"Lamarca J, Parashar S, Bartoli A, Montiel J (2020) Defslam: Tracking and mapping of deforming scenes from monocular sequences. IEEE Trans Rob 37(1):291-303","journal-title":"IEEE Trans Rob"},{"issue":"4","key":"3549_CR24","doi-asserted-by":"publisher","first-page":"4068","DOI":"10.1109\/LRA.2018.2856519","volume":"3","author":"J Song","year":"2018","unstructured":"Song J, Wang J, Zhao L, Huang S, Dissanayake G (2018) MIS-SLAM: Real-time large-scale dense deformable SLAM system in minimal invasive surgery based on heterogeneous computing. IEEE Robot Autom Lett 3(4):4068\u20134075","journal-title":"IEEE Robot Autom Lett"},{"issue":"7","key":"3549_CR25","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1007\/s11548-021-02409-x","volume":"16","author":"A Sengupta","year":"2021","unstructured":"Sengupta A, Bartoli A (2021) Colonoscopic 3D reconstruction by tubular non-rigid structure-from-motion. Int J Comput Assist Radiol Surg 16(7):1237\u20131241","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3549_CR26","doi-asserted-by":"crossref","unstructured":"Zhou H, Jayender J (2021) Emdq-slam: Real-time high-resolution reconstruction of soft tissue surface from stereo laparoscopy videos. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part IV 24, pp 331\u2013340. Springer","DOI":"10.1007\/978-3-030-87202-1_32"},{"key":"3549_CR27","doi-asserted-by":"publisher","first-page":"4252","DOI":"10.1109\/TRO.2024.3422004","volume":"40","author":"JJG Rodriguez","year":"2024","unstructured":"Rodriguez JJG, Montiel JM, Tard\u00f3s JD (2024) NR-SLAM: Nonrigid monocular SLAM. IEEE Trans Rob 40:4252\u20134264","journal-title":"IEEE Trans Rob"},{"key":"3549_CR28","unstructured":"Li Q, Yang S, Shen D, Jin Y (2024) Free-DyGS: Camera-Pose-Free Scene Reconstruction based on Gaussian Splatting for Dynamic Surgical Videos. arXiv preprint"},{"key":"3549_CR29","doi-asserted-by":"crossref","unstructured":"Wang K, Yang C, Wang Y, Li S, Wang Y, Dou Q, Yang X, Shen W (2024) Endogslam: Real-time dense reconstruction and tracking in endoscopic surgeries using gaussian splatting. In: Int Conf Med Image Comput Computer-Assis Intervent (MICCAI), pp 219\u2013229. Springer","DOI":"10.1007\/978-3-031-72089-5_21"},{"issue":"4","key":"3549_CR30","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl B, Kopanas G, Leimk\u00fchler T, Drettakis G (2023) 3D gaussian splatting for real-time radiance field rendering. ACM Trans Graph 42(4):139\u20131","journal-title":"ACM Trans Graph"},{"key":"3549_CR31","doi-asserted-by":"crossref","unstructured":"Teed Z, Deng J (2020) RAFT: Recurrent all-pairs field transforms for optical flow. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16, pp. 402\u2013419. Springer","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"3549_CR32","doi-asserted-by":"crossref","unstructured":"Shvets AA, Rakhlin A, Kalinin AA, Iglovikov VI (2018) Automatic instrument segmentation in robot-assisted surgery using deep learning. In: 2018 17th IEEE Int Conf Mach Learn Appl (ICMLA), pp 624\u2013628. IEEE","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"3549_CR33","unstructured":"Hong W-Y, Kao C-L, Kuo Y-H, Wang J-R, Chang W-L, Shih C-S (2020) Cholecseg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80. arXiv preprint arXiv:2012.12453"},{"key":"3549_CR34","unstructured":"Allan M, Mcleod J, Wang C, Rosenthal JC, Hu Z, Gard N, Eisert P, Fu KX, Zeffiro T, Xia W, et al (2021) Stereo correspondence and reconstruction of endoscopic data challenge. arXiv preprint arXiv:2101.01133"},{"issue":"4","key":"3549_CR35","doi-asserted-by":"publisher","first-page":"7225","DOI":"10.1109\/LRA.2021.3095528","volume":"6","author":"D Recasens","year":"2021","unstructured":"Recasens D, Lamarca J, F\u00e1cil JM, Montiel JM, Civera J (2021) Endo-Depth-and-Motion: Reconstruction and tracking in endoscopic videos using depth networks and photometric constraints. IEEE Robo Autom Lett 6(4):7225\u20137232","journal-title":"IEEE Robo Autom Lett"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03549-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03549-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03549-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T01:30:53Z","timestamp":1779413453000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03549-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,22]]},"references-count":35,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["3549"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03549-0","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,22]]},"assertion":[{"value":"11 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2025","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 that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}