{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:03Z","timestamp":1777865463240,"version":"3.51.4"},"reference-count":51,"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\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-2127544,IIS-2433768"],"award-info":[{"award-number":["IIS-2127544,IIS-2433768"]}],"id":[{"id":"10.13039\/100000001","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\/iccv51701.2025.01664","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17909-17919","source":"Crossref","is-referenced-by-count":0,"title":["Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers"],"prefix":"10.1109","author":[{"given":"Divyansh","family":"Srivastava","sequence":"first","affiliation":[{"name":"UC San Diego,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"UC San Diego,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Wen","sequence":"additional","affiliation":[{"name":"Tsingua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenru","family":"Wen","sequence":"additional","affiliation":[{"name":"Tsingua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuowen","family":"Tu","sequence":"additional","affiliation":[{"name":"UC San Diego,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01343"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01236"},{"key":"ref3","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01760"},{"key":"ref5","article-title":"Pixart-$alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref7","article-title":"On the importance of noise scheduling for diffusion models","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"ref9","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","volume-title":"The Eleventh International Conference on Learning Representations","author":"Couairon","year":"2023"},{"key":"ref10","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":"ref11","volume-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref14","article-title":"Llm blueprint: Enabling text-to-image generation with complex and detailed prompts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gani","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00104"},{"key":"ref16","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Advances in Neural Information Processing Systems","author":"Heusel","year":"2017"},{"key":"ref17","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","author":"Ho","year":"2020"},{"key":"ref19","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00980"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01765"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00999"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_29"},{"key":"ref25","article-title":"Generating graphic layouts with wireframe discriminator","volume-title":"International Conference on Learning Representations","author":"Li","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref27","article-title":"LLMgrounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2973"},{"key":"ref32","article-title":"Sentencet5: Scalable sentence encoders from pre-trained text-to-text models","author":"Ni","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref33","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Nichol","year":"2021"},{"key":"ref34","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Nichol","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref37","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"issue":"140","key":"ref40","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref41","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_19"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref47","first-page":"10628","article-title":"Bayesian diffusion models for 3d shape reconstruction","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Haiyang","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1806"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01369"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00664"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"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\/11444677.pdf?arnumber=11444677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:37:22Z","timestamp":1777531042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444677\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01664","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}