{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:01:55Z","timestamp":1777888915463,"version":"3.51.4"},"reference-count":91,"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\/iccv51701.2025.02384","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25700-25711","source":"Crossref","is-referenced-by-count":0,"title":["Autoscape: Geometry-Consistent Long-Horizon Scene Generation"],"prefix":"10.1109","author":[{"given":"Jiacheng","family":"Chen","sequence":"first","affiliation":[{"name":"Simon Fraser University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"NEC Labs America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingfu","family":"Liang","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingbing","family":"Zhuang","sequence":"additional","affiliation":[{"name":"NEC Labs America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong-Chyi","family":"Su","sequence":"additional","affiliation":[{"name":"NEC Labs America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sparsh","family":"Garg","sequence":"additional","affiliation":[{"name":"NEC Labs America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Wu","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manmohan","family":"Chandraker","sequence":"additional","affiliation":[{"name":"NEC Labs America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos-transfer1: Conditional world generation with adaptive multimodal control","author":"Abu Alhaija","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_6"},{"key":"ref9","article-title":"Blenderfusion: 3d-grounded visual editing and generative compositing","author":"Chen","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"Omnire: Omni urban scene reconstruction","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657513"},{"key":"ref13","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00069"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1734"},{"key":"ref16","article-title":"Magicdrive: Street view generation with diverse 3d geometry control","author":"Gao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Magicdrive-v2: High-resolution long video generation for autonomous driving with adaptive control","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","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 (NeurIPS)"},{"key":"ref21","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref24","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref28","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00908"},{"key":"ref31","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"ref33","article-title":"4k4dgen: Panoramic 4d generation at 4k resolution","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Drive-1-to-3: Enriching diffusion priors for novel view synthesis of real vehicles","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref36","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680764"},{"key":"ref38","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref39","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610324"},{"key":"ref42","article-title":"Infinicube: Unbounded and controllable dynamic 3d driving scene generation with world-guided video models","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref44","article-title":"Trajectorycrafter: Redirecting camera trajectory for monocular videos via diffusion models","volume":"2","author":"Mark","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0155"},{"key":"ref46","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref47","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01396"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.4324\/9780367262051-8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00593"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00529"},{"key":"ref57","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning (ICML)","author":"Sohl-Dickstein","year":"2015"},{"key":"ref58","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref59","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref61","article-title":"Ldm3d: Latent diffusion model for 3d","author":"Stan","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01850"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368234"},{"key":"ref64","article-title":"Mvdiffusion: Enabling holistic multi-view image generation with correspondence-aware diffusion","author":"Tang","year":"2023","journal-title":"arXiv, abs\/2307.01097"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_10"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01411"},{"key":"ref67","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref69","article-title":"Omniedit: Building image editing generalist models through specialist supervision","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR)","author":"Wei","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref71","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref73","article-title":"Neural assets: 3d-aware multi-object scene synthesis with image diffusion models","author":"Wu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32951"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_10"},{"key":"ref76","article-title":"Emernerf: Emergent spatial-temporal scene decomposition via self-supervision","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref77","article-title":"Bevcontrol: Accurately controlling street-view elements with multi-perspective consistency via bev sketch layout","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref78","article-title":"Drivearena: A closed-loop generative simulation platform for autonomous driving","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00555"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00719"},{"key":"ref85","article-title":"Lion: Latent point diffusion models for 3d shape generation","author":"Zeng","year":"2022","journal-title":"arXiv, abs\/2210.06978"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref87","article-title":"Learning unsupervised world models for autonomous driving via discrete diffusion","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01122"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_19"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1956"}],"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\/11445552.pdf?arnumber=11445552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:21Z","timestamp":1777611741000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02384","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}