{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:05:01Z","timestamp":1782795901400,"version":"3.54.5"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687518","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["PGDM: Multimodal Panoramic Image Generation with Diffusion Models"],"prefix":"10.1109","author":[{"given":"Depei","family":"Liu","sequence":"first","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongjie","family":"Fan","sequence":"additional","affiliation":[{"name":"China University of Political Science and Law,The Department of Science and Technology Teaching,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfei","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University,National Engineering Research Center for Software Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"ICLR","author":"Brock"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref5","first-page":"14837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"Razavi","year":"2019","journal-title":"NeurIPS"},{"key":"ref6","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30"},{"key":"ref7","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref8","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"ref10","article-title":"Scenescape: Text-driven consistent scene generation","author":"Fridman","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref12","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref13","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","journal-title":"ICML, 2021"},{"key":"ref14","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","journal-title":"ICML, 2021"},{"key":"ref16","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555447"},{"key":"ref20","first-page":"1737","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","volume-title":"ICML","author":"Bar-Tal"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00982"},{"key":"ref22","article-title":"Mvdiffusion: Enabling holistic multi-view image generation with correspondence-aware diffusion","author":"Tang","year":"2023"},{"key":"ref23","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma"},{"key":"ref24","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref28","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref29","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687518.pdf?arnumber=10687518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:12:54Z","timestamp":1727763174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687518","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}