{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:54:43Z","timestamp":1782392083830,"version":"3.54.5"},"reference-count":38,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Youth Innovation Team of Shaanxi Universities of Xi\u2019an University of Architecture and Technology Huaqing College"},{"name":"School-level Special Project on Artificial Intelligence Empowering Education and Teaching Reform of Xi\u2019an University of Architecture and Technology Huaqing College"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate monocular depth estimation (MDE) is a foundational task in endoscopic surgery, critical for augmenting depth perception and aiding surgical navigation. While diffusion-based and discriminative depth estimators demonstrate complementary strengths, they also exhibit asymmetric errors: discriminative models yield precise geometric boundaries but struggle in homogeneous or saturated areas, whereas diffusion models recover fine textures at the cost of occasional structural incoherence. To systematically exploit this complementarity, we present CoDepth, a novel framework that leverages confidence-guided fusion to harmonize the outputs of these heterogeneous estimators. Its core components include a complementary map extractor that identifies structured disparity disagreements, a cross-attention module for context-aware feature integration, and a probabilistic confidence network that generates spatially adaptive fusion weights. Extensive evaluations on the SCARED dataset show that CoDepth achieves improved overall performance relative to strong single-model baselines, with the most consistent gains observed in Abs Rel and \u03b4-based accuracy, while changes in some other error metrics are more modest. Furthermore, CoDepth exhibits encouraging cross-domain generalization. When a model trained on SCARED is directly evaluated on SERV-CT, Hamlyn, and C3VD without fine-tuning, it achieves competitive performance and improves several key metrics across datasets. The framework also demonstrates enhanced robustness against common synthetic corruptions like low-light conditions, Gaussian noise, and impulse noise, underscoring its practical utility in complex clinical settings. These results suggest that confidence-guided complementary fusion provides a practical integration-level paradigm for combining heterogeneous endoscopic depth estimators.<\/jats:p>","DOI":"10.3390\/s26134033","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:37:55Z","timestamp":1782391075000},"page":"4033","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Confidence-Guided Fusion for Self-Supervised Monocular Depth Estimation in Endoscopy"],"prefix":"10.3390","volume":"26","author":[{"given":"Shuang","family":"Li","sequence":"first","affiliation":[{"name":"School of Information and Artificial Intelligence, Xi\u2019an University of Architecture and Technology Huaqing College, Xi\u2019an 710043, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Xi\u2019an University of Architecture and Technology Huaqing College, Xi\u2019an 710043, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxu","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Xi\u2019an University of Architecture and Technology Huaqing College, Xi\u2019an 710043, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Xi\u2019an University of Architecture and Technology Huaqing College, Xi\u2019an 710043, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4145-8395","authenticated-orcid":false,"given":"Yingping","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi\u2019an 710071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Information and Control Engineering, Xi\u2019an University of Architecture and Technology, Xi\u2019an 710055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Umirzakova, S., Muksimova, S., Mardieva, S., Sultanov Baxtiyarovich, M., and Cho, Y.I. (2024). MIRA-CAP: Memory-Integrated Retrieval-Augmented captioning for State-of-the-Art image and video captioning. Sensors, 24.","DOI":"10.3390\/s24248013"},{"key":"ref_2","unstructured":"Lee, W., Park, N., and Woo, W. (2011, January 28\u201330). Depth-assisted real-time 3D object detection for augmented reality. Proceedings of the ICAT, Osaka, Japan."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Hazirbas, C., Ma, L., Domokos, C., and Cremers, D. (2016). Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture. Proceedings of the Asian Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"102338","DOI":"10.1016\/j.media.2021.102338","article-title":"Self-supervised monocular depth and ego-motion estimation in endoscopy: Appearance flow to the rescue","volume":"77","author":"Shao","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1438","DOI":"10.1109\/TMI.2019.2950936","article-title":"Dense depth estimation in monocular endoscopy with self-supervised learning methods","volume":"39","author":"Liu","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1080\/21681163.2021.2012835","article-title":"Depth estimation from single-shot monocular endoscope image using image domain adaptation and edge-aware depth estimation","volume":"10","author":"Oda","year":"2022","journal-title":"Comput. Methods Biomech. Biomed. Eng. Imaging Vis."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Li, Y. (2023). Endodepthl: Lightweight endoscopic monocular depth estimation with cnn-transformer. Proceedings of the 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE.","DOI":"10.1109\/BIBM58861.2023.10386008"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3664","DOI":"10.1109\/TCSVT.2024.3509619","article-title":"MonoDiffusion: Self-supervised monocular depth estimation using diffusion model","volume":"35","author":"Shao","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_9","unstructured":"Lu, D., Xiao, D., Ai, D., Fan, J., Fu, T., Lin, Y., Song, H., Ye, X., Zhang, L., and Yang, J. (2025). MetaFE-DE: Learning Meta Feature Embedding for Depth Estimation from Monocular Endoscopic Images. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1007\/s11548-025-03333-0","article-title":"SfMDiffusion: Self-supervised monocular depth estimation in endoscopy based on diffusion models","volume":"20","author":"Li","year":"2025","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_11","unstructured":"Garg, R., Bg, V.K., Carneiro, G., and Reid, I. (2016). Unsupervised cnn for single view depth estimation: Geometry to the rescue. Proceedings of the Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11\u201314 October 2016, Springer. Proceedings, Part VIII 14."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., and Brostow, G.J. (2017). Unsupervised monocular depth estimation with left-right consistency. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., and Lowe, D.G. (2017). Unsupervised learning of depth and ego-motion from video. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., and Brostow, G.J. (2019). Digging into self-supervised monocular depth estimation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref_15","unstructured":"Bian, J., Li, Z., Wang, N., Zhan, H., Shen, C., Cheng, M.M., and Reid, I. (2019, January 8\u201314). Unsupervised scale-consistent depth and ego-motion learning from monocular video. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Johnston, A., and Carneiro, G. (2020). Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7565","DOI":"10.1109\/TCSVT.2023.3275584","article-title":"Self-supervised monocular depth estimation with self-reference distillation and disparity offset refinement","volume":"33","author":"Liu","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"107619","DOI":"10.1016\/j.cmpb.2023.107619","article-title":"Self-supervised monocular depth estimation for gastrointestinal endoscopy","volume":"238","author":"Liu","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, N., Nex, F., Vosselman, G., and Kerle, N. (2023). Lite-mono: A lightweight cnn and transformer architecture for self-supervised monocular depth estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1934","DOI":"10.1109\/TMI.2024.3352390","article-title":"Self-supervised lightweight depth estimation in endoscopy combining cnn and transformer","volume":"43","author":"Yang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_21","unstructured":"Xu, Z., Li, B., Hu, Y., Zhang, C., East, J., Ali, S., and Rittscher, J. (2024). Self-supervised Monocular Depth and Pose Estimation for Endoscopy with Generative Latent Priors. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e70035","DOI":"10.1049\/ipr2.70035","article-title":"Enhancing Self-Supervised Monocular Depth Estimation in Endoscopy via Feature-Based Perceptual Loss","volume":"19","author":"Zhu","year":"2025","journal-title":"IET Image Process."},{"key":"ref_23","unstructured":"Saxena, S., Kar, A., Norouzi, M., and Fleet, D.J. (2023). Monocular depth estimation using diffusion models. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Duan, Y., Guo, X., and Zhu, Z. (2024). Diffusiondepth: Diffusion denoising approach for monocular depth estimation. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Peebles, W., and Xie, S. (2023). Scalable diffusion models with transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_27","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention Is All You Need. arXiv."},{"key":"ref_28","unstructured":"Allan, M., Mcleod, J., Wang, C., Rosenthal, J.C., Hu, Z., Gard, N., Eisert, P., Fu, K.X., Zeffiro, T., and Xia, W. (2021). Stereo correspondence and reconstruction of endoscopic data challenge. arXiv."},{"key":"ref_29","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_30","doi-asserted-by":"crossref","unstructured":"Behley, J., Milioto, A., and Stachniss, C. (2021). A benchmark for LiDAR-based panoptic segmentation based on KITTI. Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE.","DOI":"10.1109\/ICRA48506.2021.9561476"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Fang, Z., Chen, X., Chen, Y., and Gool, L.V. (2020). Towards Good Practice for CNN-Based Monocular Depth Estimation. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE.","DOI":"10.1109\/WACV45572.2020.9093334"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Spencer, J., Bowden, R., and Hadfield, S. (2020). Defeat-net: General monocular depth via simultaneous unsupervised representation learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.01441"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"102058","DOI":"10.1016\/j.media.2021.102058","article-title":"EndoSLAM dataset and an unsupervised monocular visual odometry and depth estimation approach for endoscopic videos","volume":"71","author":"Ozyoruk","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Huang, Y., Li, W., Cui, Z., Hu, Y., and Li, Z. (2026). An Adaptive Finite-Time Convergent Neural Network With Enhanced Joint Limit Constraints for 3-DoF Visual Servoing of Rigid-Flexible Coupling Robots. IEEE Trans. Ind. Electron., Early Access.","DOI":"10.1109\/TIE.2026.3679764"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2250","DOI":"10.1109\/LRA.2022.3143305","article-title":"A surgeon preference-guided autonomous instrument tracking method with a robotic flexible endoscope based on dVRK platform","volume":"7","author":"Huang","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, A., Yin, H., Cui, B., Xu, M., and Ren, H. (2024). Benchmarking robustness of endoscopic depth estimation with synthetically corrupted data. Proceedings of the International Workshop on Simulation and Synthesis in Medical Imaging, Springer.","DOI":"10.1007\/978-3-031-73281-2_5"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1109\/TSMC.2024.3492324","article-title":"An accelerated anti-noise adaptive neural network for robotic flexible endoscope with multitype surgical objectives and constraints","volume":"55","author":"Huang","year":"2024","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1109\/TMECH.2023.3286850","article-title":"4-DOF visual servoing of a robotic flexible endoscope with a predefined-time convergent and noise-immune adaptive neural network","volume":"29","author":"Huang","year":"2023","journal-title":"IEEE\/ASME Trans. Mechatron."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4033\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:40:36Z","timestamp":1782391236000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4033"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":38,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134033"],"URL":"https:\/\/doi.org\/10.3390\/s26134033","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]}}}