{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:19:10Z","timestamp":1783106350343,"version":"3.54.6"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42576200"],"award-info":[{"award-number":["42576200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014103","name":"Key Technology Research and Development Program of Shandong","doi-asserted-by":"publisher","award":["2024ZLGX06"],"award-info":[{"award-number":["2024ZLGX06"]}],"id":[{"id":"10.13039\/100014103","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114232","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:34:00Z","timestamp":1781278440000},"page":"114232","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["UMDM-USG: A unified multi-view diffusion model for underwater scene generation via cross-view representation alignment"],"prefix":"10.1016","volume":"180","author":[{"given":"Yifan","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengjia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinghui","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114232_b1","doi-asserted-by":"crossref","unstructured":"S. Lian, H. Li, R. Cong, S. Li, W. Zhang, S. Kwong, WaterMask: Instance Segmentation for Underwater Imagery, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 1305\u20131315.","DOI":"10.1109\/ICCV51070.2023.00126"},{"key":"10.1016\/j.patcog.2026.114232_b2","series-title":"Diving into underwater: Segment anything model guided underwater salient instance segmentation and a large-scale dataset","author":"Lian","year":"2024"},{"key":"10.1016\/j.patcog.2026.114232_b3","series-title":"European Conference on Computer Vision","first-page":"239","article-title":"Marineinst: A foundation model for marine image analysis with instance visual description","author":"Zheng","year":"2024"},{"key":"10.1016\/j.patcog.2026.114232_b4","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.neucom.2022.10.039","article-title":"Rethinking general underwater object detection: Datasets, challenges, and solutions","volume":"517","author":"Fu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114232_b5","series-title":"FLSea: Underwater visual-inertial and stereo-vision forward-looking datasets","author":"Randall","year":"2023"},{"key":"10.1016\/j.patcog.2026.114232_b6","doi-asserted-by":"crossref","unstructured":"D. Akkaynak, T. Treibitz, Sea-Thru: A Method for Removing Water From Underwater Images, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019.","DOI":"10.1109\/CVPR.2019.00178"},{"key":"10.1016\/j.patcog.2026.114232_b7","doi-asserted-by":"crossref","unstructured":"D. Levy, A. Peleg, N. Pearl, D. Rosenbaum, D. Akkaynak, S. Korman, T. Treibitz, SeaThru-NeRF: Neural Radiance Fields in Scattering Media, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 56\u201365.","DOI":"10.1109\/CVPR52729.2023.00014"},{"key":"10.1016\/j.patcog.2026.114232_b8","series-title":"Real-world underwater enhancement: Challenges, benchmarks, and solutions","author":"Liu","year":"2019"},{"key":"10.1016\/j.patcog.2026.114232_b9","article-title":"Partial multiview incomplete multilabel learning via uncertainty-driven reliable dynamic fusion","author":"Wen","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114232_b10","article-title":"MPR-net: Medicinal plant recognition network with dual-branch attention fusion","author":"Tang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114232_b11","doi-asserted-by":"crossref","unstructured":"F. Zhang, S. You, Y. Li, Y. Fu, Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 11852\u201311861.","DOI":"10.1109\/CVPR52733.2024.01126"},{"key":"10.1016\/j.patcog.2026.114232_b12","doi-asserted-by":"crossref","unstructured":"H. Lin, D. Liang, Z. Qi, X. Bai, A Unified Image-Dense Annotation Generation Model for Underwater Scenes, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 961\u2013970.","DOI":"10.1109\/CVPR52734.2025.00098"},{"issue":"2","key":"10.1016\/j.patcog.2026.114232_b13","doi-asserted-by":"crossref","first-page":"3227","DOI":"10.1109\/LRA.2020.2974710","article-title":"Fast underwater image enhancement for improved visual perception","volume":"5","author":"Islam","year":"2020","journal-title":"IEEE Robot. Autom. Lett. (RA-L)"},{"key":"10.1016\/j.patcog.2026.114232_b14","doi-asserted-by":"crossref","first-page":"4376","DOI":"10.1109\/TIP.2019.2955241","article-title":"An underwater image enhancement benchmark dataset and beyond","author":"Li","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114232_b15","doi-asserted-by":"crossref","unstructured":"M.J. Islam, C. Edge, Y. Xiao, P. Luo, M. Mehtaz, C. Morse, S.S. Enan, J. Sattar, Semantic Segmentation of Underwater Imagery: Dataset and Benchmark, in: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS, 2020, pp. 1769\u20131776.","DOI":"10.1109\/IROS45743.2020.9340821"},{"issue":"1","key":"10.1016\/j.patcog.2026.114232_b16","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s44295-025-00059-2","article-title":"Stabilizing underwater acoustic data generation with generative adversarial network","volume":"3","author":"Lyu","year":"2025","journal-title":"Intell. Mar. Technol. Syst."},{"issue":"2","key":"10.1016\/j.patcog.2026.114232_b17","doi-asserted-by":"crossref","first-page":"1978","DOI":"10.1109\/TPAMI.2025.3621250","article-title":"Causal interventional prompt tuning for few-shot out-of-distribution generalization","volume":"48","author":"Wen","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114232_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112737","article-title":"MKGPL: graph prompt learning with multi-view knowledge for few-shot recognition","volume":"172","author":"Xie","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114232_b19","doi-asserted-by":"crossref","unstructured":"A. Abdullah, T. Barua, R. Tibbetts, Z. Chen, M.J. Islam, I. Rekleitis, CaveSeg: Deep Semantic Segmentation and Scene Parsing for Autonomous Underwater Cave Exploration, in: 2024 IEEE International Conference on Robotics and Automation, ICRA, 2024, pp. 3781\u20133788.","DOI":"10.1109\/ICRA57147.2024.10611543"},{"key":"10.1016\/j.patcog.2026.114232_b20","article-title":"Underwater image restoration via contrastive learning and a real-world dataset","author":"Han","year":"2022","journal-title":"Remote. Sens."},{"key":"10.1016\/j.patcog.2026.114232_b21","doi-asserted-by":"crossref","first-page":"11113","DOI":"10.1109\/TCSVT.2025.3574860","article-title":"Perception-aware underwater image quality assessment: Dataset, perceptual quality scores, and assessment network","author":"Lin","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"4","key":"10.1016\/j.patcog.2026.114232_b22","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114232_b23","series-title":"European Conference on Computer Vision","first-page":"366","article-title":"Evaluating text-to-visual generation with image-to-text generation","author":"Lin","year":"2024"},{"key":"10.1016\/j.patcog.2026.114232_b24","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.114232_b25","series-title":"European Conference on Computer Vision","first-page":"370","article-title":"Sharegpt4v: Improving large multi-modal models with better captions","author":"Chen","year":"2024"},{"key":"10.1016\/j.patcog.2026.114232_b26","series-title":"MarineGPT: Unlocking secrets of ocean to the public","author":"Zheng","year":"2023"},{"key":"10.1016\/j.patcog.2026.114232_b27","series-title":"Gemma 3 technical report","author":"Team","year":"2025"},{"key":"10.1016\/j.patcog.2026.114232_b28","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.114232_b29","series-title":"SPDA-SAM: A self-prompted depth-aware segment anything model for instance segmentation","author":"Shang","year":"2026"},{"key":"10.1016\/j.patcog.2026.114232_b30","series-title":"Depth anything with any prior","author":"Wang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114232_b31","doi-asserted-by":"crossref","unstructured":"J. Wang, M. Chen, N. Karaev, A. Vedaldi, C. Rupprecht, D. Novotny, VGGT: Visual Geometry Grounded Transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 5294\u20135306.","DOI":"10.1109\/CVPR52734.2025.00499"},{"issue":"6","key":"10.1016\/j.patcog.2026.114232_b32","doi-asserted-by":"crossref","DOI":"10.1145\/3687971","article-title":"StableNormal: Reducing diffusion variance for stable and sharp normal","volume":"43","author":"Ye","year":"2024","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.patcog.2026.114232_b33","doi-asserted-by":"crossref","unstructured":"G. Bae, A.J. Davison, Rethinking Inductive Biases for Surface Normal Estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 9535\u20139545.","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"10.1016\/j.patcog.2026.114232_b34","series-title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction","author":"He","year":"2025"},{"key":"10.1016\/j.patcog.2026.114232_b35","unstructured":"E. Xie, J. Chen, J. Chen, H. Cai, H. Tang, Y. Lin, Z. Zhang, M. Li, L. Zhu, Y. Lu, et al., SANA: Efficient high-resolution text-to-image synthesis with linear diffusion transformers, in: The Thirteenth International Conference on Learning Representations, 2025."},{"key":"10.1016\/j.patcog.2026.114232_b36","series-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114232_b37","series-title":"Jodi: Unification of visual generation and understanding via joint modeling","author":"Xu","year":"2025"},{"key":"10.1016\/j.patcog.2026.114232_b38","series-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"10.1016\/j.patcog.2026.114232_b39","series-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"10.1016\/j.patcog.2026.114232_b40","series-title":"European Conference on Computer Vision","first-page":"74","article-title":"Pixart-\u03c3: Weak-to-strong training of diffusion transformer for 4K text-to-image generation","author":"Chen","year":"2025"},{"key":"10.1016\/j.patcog.2026.114232_b41","doi-asserted-by":"crossref","unstructured":"J. Han, J. Liu, Y. Jiang, B. Yan, Y. Zhang, Z. Yuan, B. Peng, X. Liu, Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 15733\u201315744.","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"10.1016\/j.patcog.2026.114232_b42","doi-asserted-by":"crossref","first-page":"8614","DOI":"10.1109\/TIP.2025.3644231","article-title":"TG-tsgnet: A text-guided arbitrary-resolution terrain scene generation network","volume":"34","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114232_b43","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"12","key":"10.1016\/j.patcog.2026.114232_b44","doi-asserted-by":"crossref","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","article-title":"No-reference image quality assessment in the spatial domain","volume":"21","author":"Mittal","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114232_b45","series-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114232_b46","series-title":"Underwater single image color restoration using haze-lines and a new quantitative dataset","author":"Berman","year":"2019"},{"key":"10.1016\/j.patcog.2026.114232_b47","series-title":"A practical approach to underwater depth and surface normals estimation","author":"Saleh","year":"2025"},{"key":"10.1016\/j.patcog.2026.114232_b48","series-title":"Evaluation of CNN-based single-image depth estimation methods","author":"Koch","year":"2018"},{"key":"10.1016\/j.patcog.2026.114232_b49","unstructured":"S.F. Bhat, I. Alhashim, P. Wonka, AdaBins: Depth Estimation Using Adaptive Bins, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 4009\u20134018."},{"key":"10.1016\/j.patcog.2026.114232_b50","doi-asserted-by":"crossref","unstructured":"W. Yuan, X. Gu, Z. Dai, S. Zhu, P. Tan, Neural Window Fully-Connected CRFs for Monocular Depth Estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 3916\u20133925.","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"10.1016\/j.patcog.2026.114232_b51","doi-asserted-by":"crossref","unstructured":"A. Agarwal, C. Arora, Attention Attention Everywhere: Monocular Depth Prediction With Skip Attention, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV, 2023, pp. 5861\u20135870.","DOI":"10.1109\/WACV56688.2023.00581"},{"key":"10.1016\/j.patcog.2026.114232_b52","doi-asserted-by":"crossref","unstructured":"Z. Xie, Z. Geng, J. Hu, Z. Zhang, H. Hu, Y. Cao, Revealing the Dark Secrets of Masked Image Modeling, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 14475\u201314485.","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"10.1016\/j.patcog.2026.114232_b53","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"vol. 34","author":"Xie","year":"2021"},{"key":"10.1016\/j.patcog.2026.114232_b54","doi-asserted-by":"crossref","unstructured":"B. Cheng, I. Misra, A.G. Schwing, A. Kirillov, R. Girdhar, Masked-Attention Mask Transformer for Universal Image Segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 1290\u20131299.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"10.1016\/j.patcog.2026.114232_b55","series-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2023"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011970?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011970?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:50:58Z","timestamp":1783104658000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326011970"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":55,"alternative-id":["S0031320326011970"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114232","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"UMDM-USG: A unified multi-view diffusion model for underwater scene generation via cross-view representation alignment","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114232","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114232"}}