{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:19:34Z","timestamp":1761895174239,"version":"build-2065373602"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209315","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Geometrically-plausible and Semantically-consistent Generation of Indoor Panoramas"],"prefix":"10.1109","author":[{"given":"Zhiliang","family":"Zeng","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Mengyang","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Xianzhi","family":"Li","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}]},{"given":"Wenzhao","family":"Gao","sequence":"additional","affiliation":[{"name":"ByteDance Inc"}]},{"given":"Shaohui","family":"Jiao","sequence":"additional","affiliation":[{"name":"ByteDance Inc"}]},{"given":"Chi-Wing","family":"Fu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"article-title":"PanoGen: Text-conditioned panoramic environment generation for vision-and-language navigation","year":"2023","author":"Li","key":"ref3"},{"article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","year":"2023","author":"Bar-Tal","key":"ref4"},{"key":"ref5","article-title":"MVDiffusion: Enabling holistic multi-view image generation with correspondence-aware diffusion","author":"Tang","year":"2023","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00486"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00607"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00982"},{"article-title":"IPO-LDM: Depth-aided 360-degree indoor rgb panorama outpainting via latent diffusion model","year":"2023","author":"Wu","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612508"},{"key":"ref11","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"article-title":"Hierarchical text-conditional image generation with clip latents","year":"2022","author":"Ramesh","key":"ref12"},{"article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","year":"2021","author":"Nichol","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00413"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-020-01426-8","article-title":"Manhattan room layout reconstruction from a single 360\u00b0 image: A comparative study of state-of-the-art methods","author":"Zou","year":"2021","journal-title":"IJCV"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00170"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.3"},{"key":"ref19","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"article-title":"The role of imagenet classes in Fr\u00e9chet Inception Distance","year":"2022","author":"Kynk\u00e4\u00e4nniemi","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01115"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_28"},{"key":"ref23","article-title":"Improved techniques for training GANs","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459199"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209315.pdf?arnumber=11209315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:45:10Z","timestamp":1761889510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209315","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}