{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:08Z","timestamp":1777865528437,"version":"3.51.4"},"reference-count":57,"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"}],"funder":[{"DOI":"10.13039\/100032443","name":"Hong Kong Jockey Club Charities Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100032443","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02311","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24922-24932","source":"Crossref","is-referenced-by-count":0,"title":["DreamCube: RGB-D Panorama Generation via Multi-Plane Synchronization"],"prefix":"10.1109","author":[{"given":"Yukun","family":"Huang","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanning","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianan","family":"Wang","sequence":"additional","affiliation":[{"name":"Astribot"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiyi","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01115"},{"key":"ref2","first-page":"1737","article-title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","volume-title":"International Conference on Machine Learning","author":"Bar-Tal","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555447"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref7","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref8","article-title":"Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models","author":"Feng","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02514"},{"key":"ref12","volume-title":"HDRIs","year":"2025"},{"key":"ref13","volume-title":"HDRIs","year":"2025"},{"key":"ref14","article-title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"ScaleCrafter: Tuning-free HigherResolution Visual Generation with Diffusion Models","volume-title":"International Conference on Learning Representations","author":"He","year":"2024"},{"key":"ref16","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Joint learning of depth and appearance for portrait image animation","author":"Ji","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref19","author":"Kalischek","year":"2025","journal-title":"Cubediff: Repurposing diffusion-based image models for panorama generation"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01085"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02620"},{"key":"ref24","volume-title":"Flux","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298715"},{"key":"ref26","article-title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-andLanguage Navigation","volume-title":"International Conference on Neural Information Processing Systems","author":"Li","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_9"},{"key":"ref28","article-title":"Hyperhuman: Hyper-realistic human generation with latent structural diffusion","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Depthlab: From partial to complete","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14755"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","volume-title":"Texture from Humus","author":"Persson","year":"2025"},{"key":"ref33","article-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","volume-title":"International Conference on Learning Representations","author":"Podell","year":"2024"},{"key":"ref34","volume-title":"HDRIs","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","article-title":"Progressive Distillation for Fast Sampling of Diffusion Models","volume-title":"International Conference on Learning Representations","author":"Salimans","year":"2022"},{"key":"ref37","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"The surprising effectiveness of diffusion models for optical flow and monocular depth estimation","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Saxena","year":"2023"},{"key":"ref39","article-title":"Monocular depth estimation using diffusion models","author":"Saxena","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"MVDream: Multi-view Diffusion for 3D Generation","volume-title":"International Conference on Learning Representations","author":"Shi","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01114"},{"key":"ref42","article-title":"LDM3D-VR: Latent Diffusion Model for 3D VR","author":"Ben","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"LDM3D: Latent Diffusion Model for 3D","author":"Ben","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"MVDiffusion: Enabling Holistic Multiview Image Generation with Correspondence-Aware Diffusion","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Tang","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00486"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612508"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4056"},{"key":"ref48","article-title":"PanoDiffusion: 360-degree Panorama Outpainting via Diffusion","volume-title":"International Conference on Learning Representations","author":"Wu","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247991"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/VR58804.2024.00085"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref53","article-title":"Diffpano: Scalable and con-sistent text to panorama generation with spherical epipolaraware diffusion","author":"Ye","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00607"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2473"}],"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\/11444886.pdf?arnumber=11444886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:34Z","timestamp":1777531594000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02311","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}