{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T14:44:51Z","timestamp":1730213091433,"version":"3.28.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20222"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0107400"],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/cvpr52729.2023.02154","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T13:30:52Z","timestamp":1692711052000},"page":"22490-22499","source":"Crossref","is-referenced-by-count":24,"title":["LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Guangcong","family":"Zheng","sequence":"first","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}]},{"given":"Xianpan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Polytechnic Institute, Zhejiang University"}]},{"given":"Xuewei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}]},{"given":"Zhongang","family":"Qi","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Image-to-image translation with conditional adver-sarial networks","author":"isola","year":"0","journal-title":"CVPR"},{"key":"ref35","article-title":"Generative modeling by estimating gradients of the data distribution","author":"song","year":"2020","journal-title":"Arxiv ArXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"ref34","article-title":"Deep unsuper-vised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"2015","journal-title":"ArXiv"},{"key":"ref15","article-title":"Learning to generate images of outdoor scenes from attributes and semantic layouts","author":"karacan","year":"2016","journal-title":"ArXiv"},{"key":"ref37","first-page":"10531","article-title":"Image synthesis from reconfig-urable layout and style","author":"sun","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref14","first-page":"1219","article-title":"Image gener-ation from scene graphs","author":"johnson","year":"0","journal-title":"CVPR"},{"key":"ref36","article-title":"Score-based generative modeling through stochastic differential equations","author":"song","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref31","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"saharia","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref30","first-page":"10684","article-title":"High-resolution image syn-thesis with latent diffusion models","author":"rombach","year":"0","journal-title":"CVPR"},{"key":"ref11","article-title":"Classifier-free diffusion guidance","author":"ho","year":"0","journal-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications"},{"key":"ref33","article-title":"Improved techniques for training gans","author":"salimans","year":"0","journal-title":"NIPS"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2022.3204461","article-title":"Image super-resolution via iterative refinement","author":"saharia","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00466"},{"key":"ref1","article-title":"Towards principled methods for training generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Denoising diffusion restoration models","author":"kawar","year":"0","journal-title":"Advances in neural information processing systems"},{"journal-title":"Rethinking the inception architecture for computer vision","year":"2015","author":"szegedy","key":"ref39"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref38","first-page":"5070","article-title":"Learning layout and style reconfig-urable gans for controllable image synthesis","volume":"44","author":"sun","year":"0","journal-title":"IEEE TPAMI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref24","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"nichol","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref23","article-title":"Mixed precision training","author":"micikevicius","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref45","article-title":"Diffusion models: A compre-hensive survey of methods and applications","author":"yang","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"Semantic image synthesis with spatially-adaptive nor-malization","author":"park","year":"0","journal-title":"CVPR"},{"key":"ref48","first-page":"754","article-title":"Entropy-driven sam-pling and training scheme for conditional diffusion generation","author":"zheng","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref25","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","author":"nichol","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00878"},{"key":"ref20","first-page":"13819","article-title":"Image synthesis from layout with localityaware mask adaption","author":"li","year":"0","journal-title":"Proceedings of the IEEE\/CVF In-ternational Conference on Computer Vision"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00763"},{"key":"ref41","article-title":"Effi-cient diffusion models for vision: A survey","author":"ulhaq","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref44","article-title":"Diffusion-based scene graph to image gener-ation with masked contrastive pre-training","author":"yang","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","author":"lu","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref43","article-title":"High-resolution image syn-thesis and semantic manipulation with conditional gans","author":"wang","year":"0","journal-title":"CVPR"},{"key":"ref28","article-title":"Classification accuracy score for conditional generative models","volume":"32","author":"ravuri","year":"0","journal-title":"Advances in Neu-ral Information Processing Systems"},{"key":"ref27","article-title":"Un-supervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Learning what and where to draw","author":"reed","year":"0","journal-title":"NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"dhariwal","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilib-rium","author":"heusel","year":"0","journal-title":"Advances in neural information processing systems"},{"journal-title":"YOLOv4 Optimal Speed and Accuracy of Object Detection","year":"2020","author":"bochkovskiy","key":"ref4"},{"key":"ref3","article-title":"Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models","author":"bao","year":"0","journal-title":"ICLRE"},{"key":"ref6","article-title":"Diffusion models in vision: A survey","author":"florinel-alin","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref40","article-title":"Text2scene: generating abstract scenes from textual descriptions","author":"tan","year":"2018","journal-title":"ArXiv"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2023,6,17]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10203809.pdf?arnumber=10203809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T13:51:50Z","timestamp":1694440310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10203809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/cvpr52729.2023.02154","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}