{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:31:05Z","timestamp":1777735865941,"version":"3.51.4"},"reference-count":109,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3628738","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T18:37:59Z","timestamp":1762281479000},"page":"4197-4211","source":"Crossref","is-referenced-by-count":2,"title":["A Survey on Text-Driven 360\u00b0 Panorama Generation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5202-208X","authenticated-orcid":false,"given":"Hai","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Statistical Science, University College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Xiang","sequence":"additional","affiliation":[{"name":"Core AI Team, Meta Reality Labs, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0087-3525","authenticated-orcid":false,"given":"Weihao","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Statistical Science, University College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1174-610X","authenticated-orcid":false,"given":"Jing-Hao","family":"Xue","sequence":"additional","affiliation":[{"name":"Department of Statistical Science, University College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00907"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"ref3","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Gu"},{"key":"ref4","article-title":"OPa-ma: Text guided mamba for 360-degree image out-painting","author":"Gao","year":"2024","journal-title":"arXiv:2407.10923"},{"key":"ref5","volume-title":"HDRIs","year":"2025"},{"key":"ref6","volume-title":"Texture From Humus","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3519021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref11","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref12","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref13","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00059"},{"key":"ref15","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round 2)","author":"Ramakrishnan"},{"key":"ref16","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref17","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref18","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.","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01085"},{"key":"ref20","article-title":"Demystifying MMD GANs","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bi\u0144kowski"},{"key":"ref21","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Podell"},{"key":"ref22","article-title":"SphereDiff: Tuning-free omnidirectional panoramic image and video generation via spherical latent representation","author":"Park","year":"2025","journal-title":"arXiv:2504.14396"},{"key":"ref23","article-title":"Omni2: Unifying omnidirectional image generation and editing in an omni model","author":"Yang","year":"2025","journal-title":"arXiv:2504.11379"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02013"},{"key":"ref25","article-title":"Conditional panoramic image generation via masked autoregressive modeling","author":"Wang","year":"2025","journal-title":"arXiv:2505.16862"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730643"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00031"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3626193"},{"key":"ref30","article-title":"HoloDreamer: Holistic 3D panoramic world generation from text descriptions","author":"Zhou","year":"2024","journal-title":"arXiv:2407.15187"},{"key":"ref31","first-page":"1173","article-title":"FastScene: Text-driven fast 3D indoor scene generation via panoramic Gaussian splatting","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Ma"},{"key":"ref32","article-title":"SceneDreamer360: Text-driven 3D-consistent scene generation with panoramic Gaussian splatting","author":"Li","year":"2024","journal-title":"arXiv:2408.13711"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_19"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref39","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref40","first-page":"1304","article-title":"DiffPano: Scalable and consistent text to panorama generation with spherical epipolar-aware diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Ye"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612508"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref44","article-title":"Cubediff: Repurposing diffusion-based image models for panorama generation","volume-title":"Proc. The 13th Int. Conf. Learn. Represent.","author":"Kalischek"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130891"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00709"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247991"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_20"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_16"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref53","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":"ref54","first-page":"2234","article-title":"Improved techniques for training gans","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref55","first-page":"1737","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bar-Tal"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555447"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00486"},{"key":"ref58","article-title":"Diffusion360: Seamless 360 degree panoramic image generation based on diffusion models","author":"Feng","year":"2023","journal-title":"arXiv:2311.13141"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00607"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29332"},{"key":"ref61","first-page":"51202","article-title":"MVDiffusion: Enabling holistic multi-view image generation with correspondence-aware diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Tang"},{"key":"ref62","article-title":"MVDream: Multi-view diffusion for 3D generation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Shi"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3485236"},{"key":"ref65","article-title":"Text-to-image diffusion models in generative AI: A survey","author":"Zhang","year":"2023","journal-title":"arXiv:2303.07909"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3522305"},{"key":"ref68","volume-title":"Free HDRI Skies,","year":"2025"},{"key":"ref69","volume-title":"HDRI Maps and Textures","year":"2025"},{"key":"ref70","volume-title":"HDRI Skies\u2013Outdoor","year":"2025"},{"key":"ref71","volume-title":"360Cities\u2013World Panoramic Photography","year":"2025"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3351601"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00208"},{"key":"ref74","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01241"},{"key":"ref77","first-page":"56424","article-title":"Autoregressive image generation without vector quantization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref78","article-title":"Autoregressive video generation without vector quantization","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Deng"},{"key":"ref79","article-title":"Large scale image completion via co-modulated generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhao"},{"key":"ref80","article-title":"What makes for text to 360-degree panorama generation with stable diffusion?","author":"Ni","year":"2025","journal-title":"arXiv:2505.22129"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00547"},{"key":"ref82","first-page":"57614","article-title":"Spherical-nested diffusion model for panoramic image outpainting","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","volume":"267","author":"Sun"},{"key":"ref83","article-title":"DreamCube: 3D panorama generation via multi-plane synchronization","author":"Huang","year":"2025","journal-title":"arXiv:2506.17206"},{"key":"ref84","volume-title":"Latentlabs360","year":"2023"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CAI59869.2024.00141"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s10055-020-00453-7"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3329119"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02391-w"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/VR58804.2024.00085"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00034"},{"key":"ref91","article-title":"ImmerseGen: Agent-guided immersive world generation with alpha-textured proxies","author":"Yuan","year":"2025","journal-title":"arXiv:2506.14315"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387307"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00660"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00576"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33089"},{"key":"ref96","article-title":"VideoPanda: Video panoramic diffusion with multi-view attention","author":"Xie","year":"2025","journal-title":"arXiv:2504.11389"},{"key":"ref97","article-title":"PanoWan: Lifting diffusion video generation models to 360\u00b0 with latitude\/longitude-aware mechanisms","author":"Xia","year":"2025","journal-title":"arXiv:2505.22016"},{"key":"ref98","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","author":"An","year":"2023","journal-title":"arXiv:2304.08477"},{"key":"ref99","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Guo"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00246"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref103","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv:2503.20314"},{"key":"ref104","article-title":"3D scene generation: A survey","author":"Wen","year":"2025","journal-title":"arXiv:2505.05474"},{"key":"ref105","article-title":"Imagine360: Immersive 360 video generation from perspective anchor","author":"Tan","year":"2024","journal-title":"arXiv:2412.03552"},{"key":"ref106","first-page":"17743","article-title":"From an image to a scene: Learning to imagine the world from a million 360 videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Wallingford"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00174"},{"key":"ref108","article-title":"VideoLLaMA 2: Advancing spatial\u2013temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024","journal-title":"arXiv:2406.07476"},{"key":"ref109","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11224934.pdf?arnumber=11224934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:02:51Z","timestamp":1775592171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11224934\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":109,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3628738","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}