{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:02Z","timestamp":1777865462285,"version":"3.51.4"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01537","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["What Makes for Text to 360-Degree Panorama Generation with Stable Diffusion?"],"prefix":"10.1109","author":[{"given":"Jinhong","family":"Ni","sequence":"first","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang-Bin","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Innovation Center of Humanoid Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Chief architect 360\u00b0 panorama renderings","year":"2025"},{"key":"ref2","volume-title":"Online 360\u00b0 panorama viewer vr","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01115"},{"key":"ref4","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555447"},{"key":"ref8","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"ICML"},{"key":"ref9","article-title":"Scaling diffusion transformers to 16 billion parameters","author":"Fei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref12","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref14","article-title":"LoRA: Low-rank adaptation of large language models","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref16","article-title":"Cubediff: Repurposing diffusion-based image models for panorama generation","author":"Kalischek","year":"2025","journal-title":"ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref18","article-title":"Panogen: Text-conditioned panoramic environment generation for vision-and-language navigation","author":"Li","year":"2023","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref20","article-title":"4k4dgen: Panoramic 4d generation at 4 k resolution","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_9"},{"key":"ref22","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref23","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29332"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_20"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref28","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2024","journal-title":"ICLR"},{"key":"ref29","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref30","article-title":"Do transformers need deep longrange memory?","author":"Rae","year":"2020","journal-title":"ACL"},{"key":"ref31","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"issue":"2","key":"ref32","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref36","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref37","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"ICLR"},{"key":"ref38","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"ICLR"},{"key":"ref39","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref40","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref42","article-title":"Mvdiffusion: Enabling holistic multiview image generation with correspondence-aware diffusion","author":"Tang","year":"2023","journal-title":"NeurIPS"},{"key":"ref43","volume-title":"Diffusers: State-of-the-art diffusion models","author":"von Platen","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_28"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00486"},{"key":"ref46","article-title":"Panodiffusion: 360 -degree panorama outpainting via diffusion","author":"Wu","year":"2024","journal-title":"ICLR"},{"key":"ref47","article-title":"Mixture of lora experts","author":"Wu","year":"2024","journal-title":"ICLR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/VR58804.2024.00085"},{"key":"ref50","article-title":"Diffpano: Scalable and consistent text to panorama generation with spherical epipolaraware diffusion","author":"Ye","year":"2024","journal-title":"NeurIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00653"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00607"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","article-title":"Unipc: A unified predictor-corrector framework for fast sampling of diffusion models","author":"Zhao","year":"2023","journal-title":"NeurIPS"},{"key":"ref55","article-title":"Dpm-solver-v3: Improved diffusion ode solver with empirical model statistics","author":"Zheng","year":"2023","journal-title":"NeurIPS"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444693.pdf?arnumber=11444693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:37:13Z","timestamp":1777531033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01537","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}