{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:48:50Z","timestamp":1776689330717,"version":"3.51.2"},"reference-count":29,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"\u201cPioneer\u201d and \u201cLeading Goose\u201d R&D Program of Zhejiang","award":["2026C02A1223"],"award-info":[{"award-number":["2026C02A1223"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Disparity estimation from stereo-endoscopic images is critical for 3D reconstruction in minimally invasive surgery (MIS). However, surgical environments have inherent interference factors including soft tissue deformation, motion blur, and photometric inconsistency. Currently, self-supervised generative networks such as StyleGAN offer an alternative method, but their reliance on iterative latent optimization leads to high computational latency and limits practical deployment. In this work, we propose a temporal latent prediction method to accelerate this optimization process. Instead of designing a brand new generator, our framework learns to predict an optimized initial latent vector, thereby reducing the number of optimization steps and per-frame inference time. Crucially, this prediction-guided mechanism does not alter the architecture or inference logic of the generator, ensuring the fidelity of reconstruction is comparable to that of the original method. Experiments on Phantom and In vivo datasets demonstrate that our method reduces average optimization steps by 16\u201359% and cuts per-frame latency by about 2.3\u00d7, compared to baseline predictors and initialization strategies. Importantly, the final photometric loss remains nearly identical across all methods, confirming that acceleration does not compromise reconstruction quality. These results position our approach as a practical step toward efficient, self-supervised stereo-endoscopic reconstruction in clinical settings.<\/jats:p>","DOI":"10.3390\/s26082529","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:01:22Z","timestamp":1776686482000},"page":"2529","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Latent Code Predictor for Accelerating Disparity Estimation in Stereo-Endoscopic Surface Reconstruction"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1089-532X","authenticated-orcid":false,"given":"Jiawei","family":"Dang","sequence":"first","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1108-4006","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7806-6029","authenticated-orcid":false,"given":"Guan","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0696-3943","authenticated-orcid":false,"given":"Chao","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Robotics, Laboratory of Computer Science, Robotics and Microelectronics of Montpellier (LIRMM), University of Montpellier, French National Center for Scientific Research (CNRS), 34095 Montpellier, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8486-1654","authenticated-orcid":false,"given":"Wenfeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1109\/TBME.2022.3195027","article-title":"Stereo Dense Scene Reconstruction and Accurate Localization for Learning-Based Navigation of Laparoscope in Minimally Invasive Surgery","volume":"70","author":"Wei","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1007\/s41315-024-00390-7","article-title":"Binocular-Based Dense 3D Reconstruction for Robotic Assisted Minimally Invasive Laparoscopic Surgery","volume":"8","author":"Sui","year":"2024","journal-title":"Int. J. Intell. Robot. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1007\/s41315-024-00404-4","article-title":"Focused Section on Advances in Robotics and Artificial Intelligence for Minimally Invasive Surgery","volume":"8","author":"Bai","year":"2024","journal-title":"Int. J. Intell. Robot. Appl."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"102380","DOI":"10.1016\/j.media.2022.102380","article-title":"StaSiS-Net: A Stacked and Siamese Disparity Estimation Network for Depth Reconstruction in Modern 3D Laparoscopy","volume":"77","author":"Bardozzo","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1016\/j.surg.2023.02.016","article-title":"National Analysis of Cost Disparities in Robotic-Assisted versus Laparoscopic Abdominal Operations","volume":"173","author":"Ng","year":"2023","journal-title":"Surgery"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"102302","DOI":"10.1016\/j.media.2021.102302","article-title":"SERV-CT: A Disparity Dataset from Cone-Beam CT for Validation of Endoscopic 3D Reconstruction","volume":"76","author":"Edwards","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zalzalah, K., Selladurai, S., and Rossa, C. (2025, January 8\u201310). Real-Time Simulation of Ultrasound Image Deformation Using Thin Plate Spline. Proceedings of the 2025 IEEE Sensors Applications Symposium (SAS), Newcastle Upon Tyne, UK.","DOI":"10.1109\/SAS65169.2025.11105189"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"5828","DOI":"10.1109\/TIP.2022.3202367","article-title":"Reconstruct Dynamic Soft-Tissue With Stereo Endoscope Based on a Single-Layer Network","volume":"31","author":"Yang","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1109\/TOH.2023.3329172","article-title":"A Survey on Force Sensing Techniques in Robot-Assisted Minimally Invasive Surgery","volume":"16","author":"Wang","year":"2023","journal-title":"IEEE Trans. Haptics"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Xu, H., and Zhang, J. (2020). AANet: Adaptive Aggregation Network for Efficient Stereo Matching. arXiv.","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chang, J.-R., and Chen, Y.-S. (2018). Pyramid Stereo Matching Network. arXiv.","DOI":"10.1109\/CVPR.2018.00567"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Diaz-Ramirez, V.H., Gonzalez-Ruiz, M., Juarez-Salazar, R., and Cazorla, M. (2025). Reliable Disparity Estimation Using Multiocular Vision with Adjustable Baseline. Sensors, 25.","DOI":"10.3390\/s25010021"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Song, Y., Liu, Y., Zhang, H., and Liu, F. (2024). High-Performance Binocular Disparity Prediction Algorithm for Edge Computing. Sensors, 24.","DOI":"10.3390\/s24144563"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Fan, X., Amiri, A.J., Fidan, B., and Jeon, S. (2023). Unsupervised Stereo Matching with Surface Normal Assistance for Indoor Depth Estimation. Sensors, 23.","DOI":"10.3390\/s23249850"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7225","DOI":"10.1109\/LRA.2021.3095528","article-title":"Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos Using Depth Networks and Photometric Constraints","volume":"6","author":"Recasens","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ji, X., Zhao, S., Liu, D., Wang, F., and Chen, X. (2025). A Robust and Effective Framework for 3D Scene Reconstruction and High-Quality Rendering in Nasal Endoscopy Surgery. Front. Neurorobotics, 19.","DOI":"10.3389\/fnbot.2025.1630728"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gil, H., Ryu, S., and Woo, S. (2024). Enhancing the Ground Truth Disparity by MAP Estimation for Developing a Neural-Net Based Stereoscopic Camera. Sensors, 24.","DOI":"10.3390\/s24237761"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xu, X., Xiang, B., Chen, G., Gong, G., and Lu, H. (2022). Transformer Based Binocular Disparity Prediction with Occlusion Predict and Novel Full Connection Layers. Sensors, 22.","DOI":"10.3390\/s22197577"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.icte.2024.09.017","article-title":"Disparity Estimation of Stereo-Endoscopic Images Using Deep Generative Network","volume":"11","author":"Yang","year":"2025","journal-title":"ICT Express"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chabra, R., Straub, J., Sweeney, C., Newcombe, R., and Fuchs, H. (2019). StereoDRNet: Dilated Residual StereoNet. arXiv.","DOI":"10.1109\/CVPR.2019.01206"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhou, C., Zhang, H., Shen, X., and Jia, J. (2017, January 22\u201329). Unsupervised Learning of Stereo Matching. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.174"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Tonioni, A., Poggi, M., Mattoccia, S., and Di Stefano, L. (2017, January 22\u201329). Unsupervised Adaptation for Deep Stereo. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.178"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1109\/LSP.2022.3154317","article-title":"Motion Prediction of Beating Heart Using Spatio-Temporal LSTM","volume":"29","author":"Zhang","year":"2022","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_24","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of the 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Stoyanov, D., Scarzanella, M.V., Pratt, P., and Yang, G.Z. (2010, January 20\u201324). Real-Time Stereo Reconstruction in Robotically Assisted Minimally Invasive Surgery. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI 2010), Beijing, China.","DOI":"10.1007\/978-3-642-15705-9_34"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Pratt, P., Stoyanov, D., Visentini-Scarzanella, M., and Yang, G.Z. (2010, January 20\u201324). Dynamic Guidance for Robotic Surgery Using Image-Constrained Biomechanical Models. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI 2010), Beijing, China.","DOI":"10.1007\/978-3-642-15705-9_10"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Stoyanov, D., Mylonas, G.P., Deligianni, F., Darzi, A., and Yang, G.Z. (2005, January 26\u201329). Soft-Tissue Motion Tracking and Structure Estimation for Robotic Assisted MIS Procedures. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI 2005), Palm Springs, CA, USA.","DOI":"10.1007\/11566489_18"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Melekhov, I., Kannala, J., and Rahtu, E. (2016, January 4\u20138). Siamese Network Features for Image Matching. Proceedings of the 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico.","DOI":"10.1109\/ICPR.2016.7899663"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2529\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:03:08Z","timestamp":1776686588000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":29,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26082529"],"URL":"https:\/\/doi.org\/10.3390\/s26082529","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]}}}