{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T04:13:46Z","timestamp":1781324026214,"version":"3.54.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42176196"],"award-info":[{"award-number":["42176196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3644231","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T19:01:46Z","timestamp":1766170906000},"page":"8614-8626","source":"Crossref","is-referenced-by-count":1,"title":["TG-TSGNet: A Text-Guided Arbitrary-Resolution Terrain Scene Generation Network"],"prefix":"10.1109","volume":"34","author":[{"given":"Yifan","family":"Zhu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1047-427X","authenticated-orcid":false,"given":"Xinghui","family":"Dong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi13070241"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77599-5_45"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrras.2023.100772"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/00029890.1984.11971507"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/15886.15890"},{"key":"ref6","article-title":"Interactive terrain rendering: Towards realism with procedural models and graphics hardware","volume-title":"Ph.D. dissertation","author":"Dachsbacher","year":"2006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/378456.378519"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/74333.74337"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2025.3536926"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref15","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00852"},{"key":"ref17","first-page":"1","article-title":"Generating images from captions with attention","volume-title":"Proc. ICLR","author":"Mansimov"},{"key":"ref18","article-title":"Generative adversarial text to image synthesis","author":"Reed","year":"2016","journal-title":"arXiv:1605.05396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref21","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2022","journal-title":"arXiv:2112.10741"},{"key":"ref22","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref23","article-title":"Dimsum: Diffusion Mamba\u2014A scalable and unified spatial-frequency method for image generation","author":"Phung","year":"2025","journal-title":"arXiv:2411.04168"},{"key":"ref24","article-title":"Vector-quantized image modeling with improved VQGAN","author":"Yu","year":"2021","journal-title":"arXiv:2110.04627"},{"key":"ref25","first-page":"2784","article-title":"Network-to-network translation with conditional invertible neural networks","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"33","author":"Rombach"},{"key":"ref26","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord"},{"key":"ref27","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref28","article-title":"Scalable autoregressive image generation with Mamba","author":"Li","year":"2025","journal-title":"arXiv:2408.12245"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00197"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00476"},{"key":"ref34","article-title":"UltraSR: Spatial encoding is a missing key for implicit image function-based arbitrary-scale super-resolution","author":"Xu","year":"2021","journal-title":"arXiv:2103.12716"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01750"},{"key":"ref36","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref37","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref38","first-page":"103031","article-title":"VMamba: Visual state space model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref43","first-page":"17413","article-title":"Scatterbrain: Unifying sparse and low-rank attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref44","article-title":"Breaking the low-rank dilemma of linear attention","author":"Fan","year":"2024","journal-title":"arXiv:2411.07635"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/DCNA53427.2021.9587279"},{"key":"ref47","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref48","first-page":"1299","article-title":"Improved techniques for training single-image GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref49","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3323799"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref53","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv:2306.09341"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Radford"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref60","article-title":"DiM: Diffusion mamba for efficient high-resolution image synthesis","author":"Teng","year":"2024","journal-title":"arXiv:2405.14224"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01467"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref64","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Li"},{"key":"ref65","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"235","author":"Esser"},{"key":"ref66","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11306245.pdf?arnumber=11306245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T18:39:51Z","timestamp":1767119991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11306245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3644231","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}