{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T13:44:16Z","timestamp":1779111856951,"version":"3.51.4"},"reference-count":56,"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\/iccv51701.2025.00336","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3520-3530","source":"Crossref","is-referenced-by-count":3,"title":["A Recipe for Generating 3D Worlds from a Single Image"],"prefix":"10.1109","author":[{"given":"Katja","family":"Schwarz","sequence":"first","affiliation":[{"name":"Meta Reality Labs,Zurich,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denis","family":"Rozumny","sequence":"additional","affiliation":[{"name":"Meta Reality Labs,Zurich,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel Rota","family":"Bul\u00f2","sequence":"additional","affiliation":[{"name":"Meta Reality Labs,Zurich,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Porzi","sequence":"additional","affiliation":[{"name":"Meta Reality Labs,Zurich,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Kontschieder","sequence":"additional","affiliation":[{"name":"Meta Reality Labs,Zurich,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/VRW62533.2024.00306"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"key":"ref3","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref5","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. of the International Conf. on Machine learning (ICML)","author":"Esser","year":"2024"},{"key":"ref6","article-title":"Diffusion360: Seamless 360 degree panoramic image generation based on diffusion models","author":"Feng","year":"2023","journal-title":"arXiv"},{"key":"ref7","article-title":"Scenescape: Text-driven consistent scene generation","author":"Fridman","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref9","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"Cascaded diffusion models for high fidelity image generation","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref13","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref15","volume-title":"Cubediff: Repurposing diffusion-based image models for panorama generation","author":"Kalischek","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref18","article-title":"Wonderland: Navigating 3d scenes from a single image","author":"Liang","year":"2024","journal-title":"arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"ref26","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol","year":"2021"},{"key":"ref27","article-title":"Panodreamer: 3d panorama synthesis from a single image","volume-title":"arXiv","author":"Paliwal","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00018"},{"key":"ref29","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"CoRR","author":"Podell","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687616"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00086"},{"key":"ref34","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer","year":"2023"},{"key":"ref35","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein","year":"2015"},{"key":"ref36","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion","author":"Sun","year":"2024","journal-title":"arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591516"},{"key":"ref39","article-title":"Mvdiffusion: Enabling holistic multiview image generation with correspondence-aware diffusion","author":"Tang","year":"2023","journal-title":"arXiv preprint 2307.01097"},{"key":"ref40","article-title":"From an image to a scene: Learning to imagine the world from a million 360\u00b0 videos","author":"Wallingford","year":"2024","journal-title":"NeurIPS"},{"key":"ref41","article-title":"Vistadream: Sampling multi-view consistent images for single-view scene reconstruction","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref43","article-title":"Moge: Unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref45","volume-title":"Worldlabs blog","year":"2024"},{"key":"ref46","article-title":"Q-align: Teaching 1 mms for visual scoring via discrete text-defined levels","volume-title":"Proc. of the International Conf. on Machine learning (ICML)","author":"Wu","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00226"},{"key":"ref48","article-title":"Florence-2: Advancing a unified representation for a variety of vision tasks","author":"Xiao","year":"2023","journal-title":"arXiv"},{"key":"ref49","article-title":"Camco: Cameracontrollable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv"},{"key":"ref50","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref52","article-title":"Wonderworld: Interactive 3d scene generation from a single image","author":"Yu","year":"2024","journal-title":"arXiv"},{"key":"ref53","article-title":"Wonderjourney: Going from anywhere to everywhere","author":"Yu","year":"2023","journal-title":"arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_19"}],"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\/11443340.pdf?arnumber=11443340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:40Z","timestamp":1777530160000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00336","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}