{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T17:02:53Z","timestamp":1784566973842,"version":"3.55.0"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"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":["62331006"],"award-info":[{"award-number":["62331006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171038"],"award-info":[{"award-number":["62171038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11263-026-02823-1","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:21:55Z","timestamp":1778167315000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Atlantis++: Enabling Underwater Depth Estimation with Stable Diffusion and Beyond"],"prefix":"10.1007","volume":"134","author":[{"given":"Fan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaodi","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6677-694X","authenticated-orcid":false,"given":"Ying","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,7]]},"reference":[{"key":"2823_CR1","doi-asserted-by":"crossref","unstructured":"Akkaynak, D., & Treibitz, T. (2018). A revised underwater image formation model. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 6723\u20136732.","DOI":"10.1109\/CVPR.2018.00703"},{"key":"2823_CR2","doi-asserted-by":"crossref","unstructured":"Akkaynak, D., & Treibitz, T. (2019). Sea-thru: A method for removing water from underwater images. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 1682\u20131691.","DOI":"10.1109\/CVPR.2019.00178"},{"key":"2823_CR3","doi-asserted-by":"crossref","unstructured":"Amer, A., Alvarez-Tunon, O., Ugurlu, H. I., Sejersen, J. L. F., Brodskiy, Y., & Kayacan, E. (2023). Unav-sim: A visually realistic underwater robotics simulator and synthetic data-generation framework. In: Proc. of International Conference on Advanced Robotics, pp 570\u2013576.","DOI":"10.1109\/ICAR58858.2023.10406819"},{"key":"2823_CR4","doi-asserted-by":"crossref","unstructured":"Amitai, S., Klein, I.,& Treibitz, T. (2023). Self-supervised monocular depth underwater. In: Proc. of International Conference on Robotics and Automation, pp 1098\u20131104.","DOI":"10.1109\/ICRA48891.2023.10161161"},{"issue":"23\u201324","key":"2823_CR5","doi-asserted-by":"publisher","first-page":"2153","DOI":"10.1016\/j.quascirev.2008.08.012","volume":"27","author":"GN Bailey","year":"2008","unstructured":"Bailey, G. N., & Flemming, N. C. (2008). Archaeology of the continental shelf: marine resources, submerged landscapes and underwater archaeology. Quaternary Science Reviews, 27(23\u201324), 2153\u20132165.","journal-title":"Quaternary Science Reviews"},{"issue":"8","key":"2823_CR6","first-page":"2822","volume":"43","author":"D Berman","year":"2020","unstructured":"Berman, D., Levy, D., Avidan, S., & Treibitz, T. (2020). Underwater single image color restoration using haze-lines and a new quantitative dataset. IEEE Trans on Pattern Analysis and Machine Intelligence, 43(8), 2822\u20132837.","journal-title":"IEEE Trans on Pattern Analysis and Machine Intelligence"},{"key":"2823_CR7","unstructured":"Bhat, S. F., Alhashim, I.,& Wonka, P. (2021). Adabins: Depth estimation using adaptive bins. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 4009\u20134018."},{"key":"2823_CR8","unstructured":"Bhat, S. F., Birkl, R., Wofk, D., Wonka, P., & M\u00fcller, M. (2023). Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv:2302.12288."},{"key":"2823_CR9","unstructured":"BlackForestLabs (2024) Flux.1-dev. https:\/\/huggingface.co\/black-forest-labs\/FLUX.1-dev"},{"key":"2823_CR10","unstructured":"Blidberg, D. R. (2001). The development of autonomous underwater vehicles (auv); a brief summary. In: Proc. of International Conference on Robotics and Automation, pp 122\u2013129."},{"key":"2823_CR11","unstructured":"Bochkovskii, A., Delaunoy, A., Germain, H., Santos, M., Zhou, Y., Richter, S. R., & Koltun, V. (2024). Depth pro: Sharp monocular metric depth in less than a second. arXiv:2410.02073."},{"key":"2823_CR12","unstructured":"Cabon, Y., Murray, N., Humenberger, M. (2020). Virtual kitti 2. arXiv:2001.10773."},{"issue":"6","key":"2823_CR13","doi-asserted-by":"publisher","first-page":"1406","DOI":"10.1007\/s11263-023-01762-5","volume":"131","author":"L Cai","year":"2023","unstructured":"Cai, L., McGuire, N. E., Hanlon, R., Mooney, T. A., & Girdhar, Y. (2023). Semi-supervised visual tracking of marine animals using autonomous underwater vehicles. International Journal of Computer Vision, 131(6), 1406\u20131427.","journal-title":"International Journal of Computer Vision"},{"issue":"4","key":"2823_CR14","doi-asserted-by":"publisher","first-page":"1756","DOI":"10.1109\/TIP.2011.2179666","volume":"21","author":"JY Chiang","year":"2011","unstructured":"Chiang, J. Y., & Chen, Y. C. (2011). Underwater image enhancement by wavelength compensation and dehazing. IEEE Trans on Image Processing, 21(4), 1756\u20131769.","journal-title":"IEEE Trans on Image Processing"},{"key":"2823_CR15","doi-asserted-by":"crossref","unstructured":"Coleman, D. F., Newman, J. B., Ballard, R. D. (2000). Design and implementation of advanced underwater imaging systems for deep sea marine archaeological surveys. In: OCEANS, pp 661\u2013665.","DOI":"10.1109\/OCEANS.2000.881329"},{"key":"2823_CR16","unstructured":"Comanici, G., Bieber, E., Schaekermann, M., Pasupat, I., Sachdeva, N., Dhillon, I., Blistein, M., Ram, O., Zhang, D., Rosen, E., et\u00a0al. (2025). Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv:2507.06261."},{"key":"2823_CR17","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2823_CR18","doi-asserted-by":"crossref","unstructured":"Digumarti, S. T., Chaurasia, G., Taneja, A., Siegwart, R., Thomas, A., & Beardsley, P. (2016). Underwater 3d capture using a low-cost commercial depth camera. In: IEEE Winter Conference on Applications of Computer Vision, pp 1\u20139.","DOI":"10.1109\/WACV.2016.7477644"},{"key":"2823_CR19","doi-asserted-by":"crossref","unstructured":"Ding, Y., Li, K., Mei, H., Liu, S., & Hou, G. (2024). Watermono: Teacher-guided anomaly masking and enhancement boosting for robust underwater self-supervised monocular depth estimation. arXiv:2406.13344.","DOI":"10.1109\/TIM.2025.3553943"},{"issue":"2","key":"2823_CR20","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/MCG.2016.26","volume":"36","author":"PL Drews","year":"2016","unstructured":"Drews, P. L., Nascimento, E. R., Botelho, S. S., & Campos, M. F. M. (2016). Underwater depth estimation and image restoration based on single images. IEEE Computer Graphics and Applications, 36(2), 24\u201335.","journal-title":"IEEE Computer Graphics and Applications"},{"issue":"2","key":"2823_CR21","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1364\/JOSA.53.000214","volume":"53","author":"SQ Duntley","year":"1963","unstructured":"Duntley, S. Q. (1963). Light in the sea. Journal of the Optical Soceity of America, 53(2), 214\u2013233.","journal-title":"Journal of the Optical Soceity of America"},{"key":"2823_CR22","doi-asserted-by":"crossref","unstructured":"Ebner, L., Billings, G., & Williams, S. (2024). Metrically scaled monocular depth estimation through sparse priors for underwater robots. In: Proc. of International Conference on Robotics and Automation, pp 3751\u20133757.","DOI":"10.1109\/ICRA57147.2024.10611007"},{"key":"2823_CR23","unstructured":"Eigen, D., Puhrsch, C., & Fergus, R. (2014). Depth map prediction from a single image using a multi-scale deep network. In: Proc. of Conference on Neural Information Processing Systems."},{"key":"2823_CR24","doi-asserted-by":"crossref","unstructured":"Filisetti, A., Marouchos, A., Martini, A., Martin, T., & Collings, S. (2018). Developments and applications of underwater lidar systems in support of marine science. In: OCEANS, pp 1\u201310.","DOI":"10.1109\/OCEANS.2018.8604547"},{"key":"2823_CR25","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., & Tao, D. (2018). Deep ordinal regression network for monocular depth estimation. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 2002\u20132011.","DOI":"10.1109\/CVPR.2018.00214"},{"key":"2823_CR26","doi-asserted-by":"crossref","unstructured":"Fu, X., Yin, W., Hu, M., Wang, K., Ma, Y., Tan, P., Shen, S., Lin, D., & Long, X. (2024). Geowizard: Unleashing the diffusion priors for 3d geometry estimation from a single image. In: Proc. of European Conference on Computer Vision, pp 241\u2013258.","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"2823_CR27","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? the kitti vision benchmark suite. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 3354\u20133361.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2823_CR28","first-page":"257","volume":"47","author":"R Gibson","year":"2016","unstructured":"Gibson, R., Atkinson, R., & Gordon, J. (2016). A review of underwater stereo-image measurement for marine biology and ecology applications. Oceanography and Marine Biology: An Annual Review, 47, 257\u2013292.","journal-title":"Oceanography and Marine Biology: An Annual Review"},{"key":"2823_CR29","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., & Brostow, G. J. (2017). Unsupervised monocular depth estimation with left-right consistency. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 270\u2013279.","DOI":"10.1109\/CVPR.2017.699"},{"key":"2823_CR30","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Firman, M., & Brostow, G. J. (2019). Digging into self-supervised monocular depth estimation. In: Proc. of International Conference on Computer Vision, pp 3828\u20133838.","DOI":"10.1109\/ICCV.2019.00393"},{"issue":"11","key":"2823_CR31","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020). Generative adversarial networks. Communications of the ACM, 63(11), 139\u2013144.","journal-title":"Communications of the ACM"},{"key":"2823_CR32","doi-asserted-by":"crossref","unstructured":"Gupta, H., & Mitra, K. (2019). Unsupervised single image underwater depth estimation. In: Proc. of IEEE International Conference on Image Processing, pp 624\u2013628.","DOI":"10.1109\/ICIP.2019.8804200"},{"key":"2823_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3120130","volume":"70","author":"P Hambarde","year":"2021","unstructured":"Hambarde, P., Murala, S., & Dhall, A. (2021). Uw-gan: Single-image depth estimation and image enhancement for underwater images. IEEE Transactions on Instrumentation and Measurement, 70, 1\u201312.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"12","key":"2823_CR34","first-page":"2341","volume":"33","author":"K He","year":"2010","unstructured":"He, K., Sun, J., & Tang, X. (2010). Single image haze removal using dark channel prior. IEEE Trans on Pattern Analysis and Machine Intelligence, 33(12), 2341\u20132353.","journal-title":"IEEE Trans on Pattern Analysis and Machine Intelligence"},{"key":"2823_CR35","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 1125\u20131134.","DOI":"10.1109\/CVPR.2017.632"},{"issue":"2","key":"2823_CR36","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/48.50695","volume":"15","author":"JS Jaffe","year":"1990","unstructured":"Jaffe, J. S. (1990). Computer modeling and the design of optimal underwater imaging systems. IEEE Journal of Oceanic Engineering, 15(2), 101\u2013111.","journal-title":"IEEE Journal of Oceanic Engineering"},{"key":"2823_CR37","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R. C., & Schindler, K. (2024). Repurposing diffusion-based image generators for monocular depth estimation. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 9492\u20139502.","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"2823_CR38","doi-asserted-by":"publisher","first-page":"4376","DOI":"10.1109\/TIP.2019.2955241","volume":"29","author":"C Li","year":"2019","unstructured":"Li, C., Guo, C., Ren, W., Cong, R., Hou, J., Kwong, S., & Tao, D. (2019). An underwater image enhancement benchmark dataset and beyond. IEEE Trans on Image Processing, 29, 4376\u20134389.","journal-title":"IEEE Trans on Image Processing"},{"key":"2823_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107038","volume":"98","author":"C Li","year":"2020","unstructured":"Li, C., Anwar, S., & Porikli, F. (2020). Underwater scene prior inspired deep underwater image and video enhancement. Pattern Recognition, 98, Article 107038.","journal-title":"Pattern Recognition"},{"key":"2823_CR40","unstructured":"Li, J., Li, D., Savarese, S., & Hoi, S. (2023). Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv:2301.12597."},{"key":"2823_CR41","unstructured":"Liu, C., Kumar, S., Gu, S., Timofte, R., & Van\u00a0Gool, L. (2022). Va-depthnet: A variational approach to single image depth prediction. In: Proc. of International Conference on Learning representations."},{"key":"2823_CR42","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023). Visual instruction tuning. arXiv:2304.08485.","DOI":"10.52202\/075280-1516"},{"key":"2823_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In: Proc. of International Conference on Computer Vision, pp 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2823_CR44","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1117\/12.958279","volume":"208","author":"B McGlamery","year":"1980","unstructured":"McGlamery, B. (1980). A computer model for underwater camera systems. Ocean Optics VI, SPIE, 208, 221\u2013231.","journal-title":"Ocean Optics VI, SPIE"},{"issue":"1","key":"2823_CR45","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/JOE.2013.2278891","volume":"39","author":"L Paull","year":"2013","unstructured":"Paull, L., Saeedi, S., Seto, M., & Li, H. (2013). Auv navigation and localization: A review. IEEE Journal of Oceanic Engineering, 39(1), 131\u2013149.","journal-title":"IEEE Journal of Oceanic Engineering"},{"key":"2823_CR46","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., Sakaridis, C., & Yu, F. (2023). idisc: Internal discretization for monocular depth estimation. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 21477\u201321487.","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"2823_CR47","unstructured":"von Platen, P., Patil, S., Lozhkov, A., Cuenca, P., Lambert, N., Rasul, K., Davaadorj, M., & Wolf, T. (2022). Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers."},{"key":"2823_CR48","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al. (2021). Learning transferable visual models from natural language supervision. In: Proc. of International Conference on Machine Learning, pp 8748\u20138763."},{"key":"2823_CR49","unstructured":"Randall, Y., & Treibitz, T. (2023). Flsea: Underwater visual-inertial and stereo-vision forward-looking datasets. arXiv:2302.12772."},{"issue":"3","key":"2823_CR50","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., & Koltun, V. (2020). Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans on Pattern Analysis and Machine Intelligence, 44(3), 1623\u20131637.","journal-title":"IEEE Trans on Pattern Analysis and Machine Intelligence"},{"key":"2823_CR51","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021). Vision transformers for dense prediction. In: Proc. of International Conference on Computer Vision, pp 12179\u201312188.","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"2823_CR52","doi-asserted-by":"crossref","unstructured":"Roberts, M., Ramapuram, J., Ranjan, A., Kumar, A., Bautista, M. A., Paczan, N., Webb, R., & Susskind, J. M. (2021). Hypersim: A photorealistic synthetic dataset for holistic indoor scene understanding. In: Proc. of International Conference on Computer Vision, pp 10912\u201310922.","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"2823_CR53","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2823_CR54","first-page":"53025","volume":"36","author":"S Shao","year":"2023","unstructured":"Shao, S., Pei, Z., Wu, X., Liu, Z., Chen, W., & Li, Z. (2023). Iebins: Iterative elastic bins for monocular depth estimation. Proc of Conference on Neural Information Processing Systems, 36, 53025\u201353037.","journal-title":"Proc of Conference on Neural Information Processing Systems"},{"key":"2823_CR55","doi-asserted-by":"crossref","unstructured":"Shao, S., Pei, Z., Chen, W., Chen, P. C., & Li, Z. (2024). Iebins: Iterative elastic bins for monocular depth estimation and completion. International Journal of Computer Vision pp 1\u201324.","DOI":"10.1007\/s11263-024-02293-3"},{"key":"2823_CR56","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor segmentation and support inference from rgbd images. In: Proc. of European Conference on Computer Vision, pp 746\u2013760.","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"2823_CR57","doi-asserted-by":"crossref","unstructured":"Song, J., Ma, H., Bagoren, O., Sethuraman, A., Zhang, Y., & Skinner, K. A. (2025). Oceansim: A gpu-accelerated underwater robot perception simulation framework. In: Proc. of International Conference on Intelligent Robots and Systems, pp 1526\u20131533.","DOI":"10.1109\/IROS60139.2025.11246878"},{"key":"2823_CR58","unstructured":"Teed, Z., & Deng, J. (2021). DROID-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras. Proc of Conference on Neural Information Processing Systems."},{"key":"2823_CR59","unstructured":"Vasiljevic, I., Kolkin, N., Zhang, S., Luo, R., Wang, H., Dai, F. Z., Daniele, A. F., Mostajabi, M., Basart, S., Walter, M. R., et\u00a0al. (2019). Diode: A dense indoor and outdoor depth dataset. arXiv:1908.00463"},{"key":"2823_CR60","unstructured":"Wang, N., Zhou, Y., Han, F., Zhu, H., & Yao, J. (2019). Uwgan: underwater gan for real-world underwater color restoration and dehazing. arXiv:1912.10269."},{"issue":"4","key":"2823_CR61","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1007\/s11263-024-02230-4","volume":"133","author":"P Wenzel","year":"2025","unstructured":"Wenzel, P., Yang, N., Wang, R., Zeller, N., & Cremers, D. (2025). 4seasons: Benchmarking visual slam and long-term localization for autonomous driving in challenging conditions. International Journal of Computer Vision, 133(4), 1564\u20131586.","journal-title":"International Journal of Computer Vision"},{"key":"2823_CR62","unstructured":"Wu, C., Li, J., Zhou, J., Lin, J., Gao, K., Yan, K., Yin, S. m., Bai, S., Xu, X., Chen, Y., et\u00a0al. (2025). Qwen-image technical report. arXiv:2508.02324."},{"issue":"7","key":"2823_CR63","doi-asserted-by":"publisher","first-page":"2401","DOI":"10.1007\/s11263-023-01979-4","volume":"132","author":"K Xian","year":"2024","unstructured":"Xian, K., Cao, Z., Shen, C., & Lin, G. (2024). Towards robust monocular depth estimation: A new baseline and benchmark. International Journal of Computer Vision, 132(7), 2401\u20132419.","journal-title":"International Journal of Computer Vision"},{"issue":"4","key":"2823_CR64","doi-asserted-by":"publisher","first-page":"1012","DOI":"10.1007\/s11263-023-01915-6","volume":"132","author":"M Xiang","year":"2024","unstructured":"Xiang, M., Dai, Y., Zhang, F., Shi, J., Tian, X., & Zhang, Z. (2024). Towards a unified network for robust monocular depth estimation: Network architecture, training strategy and dataset. International Journal of Computer Vision, 132(4), 1012\u20131028.","journal-title":"International Journal of Computer Vision"},{"key":"2823_CR65","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., & Zhao, H. (2024a). Depth anything: Unleashing the power of large-scale unlabeled data. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 10371\u201310381.","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"2823_CR66","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., & Zhao, H. (2024b). Depth anything v2. arXiv:2406.09414.","DOI":"10.52202\/079017-0688"},{"key":"2823_CR67","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1016\/j.neucom.2022.09.122","volume":"514","author":"X Yang","year":"2022","unstructured":"Yang, X., Zhang, X., Wang, N., Xin, G., & Hu, W. (2022). Underwater self-supervised depth estimation. Neurocomputing, 514, 362\u2013373.","journal-title":"Neurocomputing"},{"key":"2823_CR68","doi-asserted-by":"crossref","unstructured":"Yu, B., Wu, J., & Islam, M. J. (2023). Udepth: Fast monocular depth estimation for visually-guided underwater robots. In: Proc. of International Conference on Robotics and Automation, pp 3116\u20133123.","DOI":"10.1109\/ICRA48891.2023.10161471"},{"key":"2823_CR69","doi-asserted-by":"crossref","unstructured":"Yuan, W., Gu, X., Dai, Z., Zhu, S., Tan, P. (2022). Neural window fully-connected crfs for monocular depth estimation. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 3916\u20133925.","DOI":"10.1109\/CVPR52688.2022.00389"},{"issue":"5","key":"2823_CR70","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1163\/156855301317033595","volume":"15","author":"J Yuh","year":"2001","unstructured":"Yuh, J., & West, M. (2001). Underwater robotics. Advanced Robotics, 15(5), 609\u2013639.","journal-title":"Advanced Robotics"},{"key":"2823_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, F., You, S., Li, Y., & Fu, Y. (2024). Atlantis: Enabling underwater depth estimation with stable diffusion. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 11852\u201311861.","DOI":"10.1109\/CVPR52733.2024.01126"},{"issue":"10","key":"2823_CR72","doi-asserted-by":"publisher","first-page":"9169","DOI":"10.1109\/TPAMI.2025.3586361","volume":"47","author":"F Zhang","year":"2025","unstructured":"Zhang, F., You, S., Li, Y., & Fu, Y. (2025). Learning rain location prior for nighttime deraining and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(10), 9169\u20139186.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2823_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., & Agrawala, M. (2023a). Adding conditional control to text-to-image diffusion models. In: Proc. of International Conference on Computer Vision, pp 3836\u20133847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2823_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, N., Nex, F., Vosselman, G., & Kerle, N. (2023b). Lite-mono: A lightweight cnn and transformer architecture for self-supervised monocular depth estimation. In: Proc. of Conference on Computer Vision and Pattern Recognition, pp 18537\u201318546.","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"2823_CR75","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2022.100510","volume":"46","author":"S Zhang","year":"2022","unstructured":"Zhang, S., Zhao, S., An, D., Liu, J., Wang, H., Feng, Y., Li, D., & Zhao, R. (2022). Visual slam for underwater vehicles: A survey. Computer Science Review, 46, Article 100510.","journal-title":"Computer Science Review"},{"key":"2823_CR76","doi-asserted-by":"publisher","first-page":"8144","DOI":"10.1109\/JSTARS.2021.3100395","volume":"14","author":"G Zhou","year":"2021","unstructured":"Zhou, G., Li, C., Zhang, D., Liu, D., Zhou, X., & Zhan, J. (2021). Overview of underwater transmission characteristics of oceanic lidar. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 8144\u20138159.","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"2823_CR77","unstructured":"Zwilgmeyer, P. G. O., Yip, M., Teigen, A. L., Mester, R., & Stahl, A. (2021). The varos synthetic underwater data set: Towards realistic multi-sensor underwater data with ground truth. In: Proc. of International Conference on Computer Vision, pp 3722\u20133730."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02823-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02823-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02823-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T16:14:34Z","timestamp":1784564074000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02823-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,7]]},"references-count":77,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2823"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02823-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,7]]},"assertion":[{"value":"22 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"260"}}