{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:12:57Z","timestamp":1777889577012,"version":"3.51.4"},"reference-count":70,"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\/iccv51701.2025.02336","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25186-25196","source":"Crossref","is-referenced-by-count":0,"title":["Large Scene Generation with Cube-Absorb Discrete Diffusion"],"prefix":"10.1109","author":[{"given":"Qianjiang Hu Wei","family":"Hu","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University,Beijing,P. R. China,100871"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Hu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University,Beijing,P. R. China,100871"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3","article-title":"Continuous-time Markov chains: An applications-oriented approach","author":"Anderson","year":"2012","journal-title":"Springer Science & Business Media"},{"key":"ref2","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume":"34","author":"Austin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2049"},{"key":"ref4","first-page":"2","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2022.109727"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321857"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref10","article-title":"Automated 3D model generation for urban environments","author":"Frueh","year":"2002","journal-title":"PhD thesis, Karlsruhe Institute of Technology, Germany"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2308"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref13","volume-title":"Diffusion with offset noise","author":"Guttenberg","year":"2023"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"7","article-title":"LRM: large reconstruction model for single image to 3D","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria","author":"Hong"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_7"},{"key":"ref17","first-page":"13916","article-title":"Make-An-Audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref18","article-title":"Shap-E: Generating conditional 3D implicit functions","volume":"1","author":"Jun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"Reversibility and stochastic networks","author":"Kelly","year":"2011","journal-title":"Cambridge University Press"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/sym8090093"},{"key":"ref21","first-page":"17391","article-title":"Autoregressive diffusion model for graph generation","volume-title":"International conference on machine learning","author":"Kong"},{"key":"ref22","article-title":"Diffusion probabilistic models for scene-scale 3D categorical data","author":"Lee","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1672"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02085"},{"key":"ref26","article-title":"Rectified flow: A marginal preserving approach to optimal transport","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72890-7_5"},{"key":"ref29","first-page":"5","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref30","article-title":"Discrete diffusion modeling by estimating the ratios of the data distribution","volume-title":"Forty-first International Conference on Machine Learning","author":"Lou"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3344758"},{"key":"ref33","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2502"},{"key":"ref35","article-title":"3D-LDM: Neural implicit 3D shape generation with latent diffusion models","author":"Nam","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2928"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1590\/0004-282x20190129"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref40","first-page":"7","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria","author":"Podell"},{"key":"ref41","first-page":"1","article-title":"DreamFusion: Text-to-3D using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda","author":"Poole"},{"key":"ref42","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Not all noises are created equally: Diffusion noise selection and optimization","author":"Qi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01215"},{"key":"ref45","first-page":"8857","article-title":"Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting","volume-title":"International Conference on Machine Learning","author":"Rasul"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"ref49","article-title":"UrbanWorld: An urban world model for 3D city generation","author":"Shang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref52","first-page":"7","article-title":"MVDream: Multi-view diffusion for 3D generation","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria","author":"Shi"},{"key":"ref53","first-page":"3","article-title":"Denoising diffusion implicit models","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria","author":"Song"},{"key":"ref54","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref55","first-page":"32211","article-title":"Consistency models","volume-title":"International Conference on Machine Learning, ICML 2023, 23\u201329","author":"Song","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2993369.2993372"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00119"},{"key":"ref58","article-title":"Score-based continuous-time discrete diffusion models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Sun"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref60","first-page":"7","article-title":"DreamGaussian: Generative gaussian splatting for efficient 3D content creation","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria","author":"Tang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref62","first-page":"24804","article-title":"CSDI: Conditional score-based diffusion models for probabilistic time series imputation","volume":"34","author":"Tashiro","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0728"},{"key":"ref64","first-page":"1","article-title":"DiGress: Discrete denoising diffusion for graph generation","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda","author":"Vignac"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3124"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188435"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00923"},{"key":"ref68","first-page":"7","article-title":"DMV3D: denoising multiview diffusion using 3D large reconstruction model","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria","author":"Xu"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01161"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"}],"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\/11446023.pdf?arnumber=11446023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:17Z","timestamp":1777612577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02336","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}