{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T23:38:14Z","timestamp":1769729894824,"version":"3.49.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005950","name":"Hong Kong University of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611235","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"16795-16802","source":"Crossref","is-referenced-by-count":2,"title":["From Bird\u2019s-Eye to Street View: Crafting Diverse and Condition-Aligned Images with Latent Diffusion Model"],"prefix":"10.1109","author":[{"given":"Xiaojie","family":"Xu","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianshuo","family":"Xu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fulong","family":"Ma","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingcong","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology(Guangzhou),Nansha District, Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3368234"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"14","key":"ref7","first-page":"71","article-title":"Dall-e: Creating images from text","volume":"8","author":"Reddy","year":"2021","journal-title":"UGC Care Group I Journal"},{"key":"ref8","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref10","article-title":"Large scale gan training for high fidelity natural image synthesis","author":"Brock","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref13","article-title":"Pose guided person image generation","volume":"30","author":"Ma","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00526"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01356"},{"key":"ref17","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref18","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref21","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref24","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385958"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01057"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_48"},{"key":"ref28","first-page":"22352","article-title":"Vectormapnet: End-to-end vectorized hd map learning","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00201978"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305148"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref37","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.15203"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-8844-3_4"},{"key":"ref40","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref41","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"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611235.pdf?arnumber=10611235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:15:31Z","timestamp":1723349731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611235","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}