{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T13:26:47Z","timestamp":1745242007547},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T00:00:00Z","timestamp":1718582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T00:00:00Z","timestamp":1718582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,17]]},"DOI":"10.1109\/cvprw63382.2024.00118","type":"proceedings-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T18:27:42Z","timestamp":1727461662000},"page":"1115-1125","source":"Crossref","is-referenced-by-count":5,"title":["LaDiffGAN: Training GANs with Diffusion Supervision in Latent Spaces"],"prefix":"10.1109","author":[{"given":"Xuhui","family":"Liu","sequence":"first","affiliation":[{"name":"Beihang University"}]},{"given":"Bohan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Beihang University"}]},{"given":"Sicheng","family":"Gao","sequence":"additional","affiliation":[{"name":"Beihang University"}]},{"given":"Shanglin","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University"}]},{"given":"Yutang","family":"Feng","sequence":"additional","affiliation":[{"name":"Beihang University"}]},{"given":"Hong","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University"}]},{"given":"Boyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University"}]},{"given":"Jianzhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology,Shenzhen,China"}]},{"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University"}]}],"member":"263","reference":[{"article-title":"Unsupervised attention-guided image-to-image translation","volume-title":"NeurIPS","author":"Mejjati","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00919"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01213"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00122"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.299"},{"article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"ICLR","author":"Baranchuk","key":"ref6"},{"article-title":"Large scale gan training for high fidelity natural image synthesis","volume-title":"ICLR","author":"Brock","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01764"},{"article-title":"Extracting training data from diffusion models","year":"2023","author":"Carlini","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.296"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00819"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01816"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","key":"ref17"},{"article-title":"Adversarial feature learning","volume-title":"ICLR","author":"Donahue","key":"ref18"},{"article-title":"Adversarially learned inference","volume-title":"ICLR","author":"Dumoulin","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00084"},{"article-title":"Prompt-to-prompt image editing with cross attention control","year":"2022","author":"Hertz","key":"ref22"},{"article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"NeurIPS","author":"Heusel","key":"ref23"},{"article-title":"Imagen video: High definition video generation with diffusion models","year":"2022","author":"Ho","key":"ref24"},{"article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","key":"ref25"},{"article-title":"Video diffusion models","volume-title":"NeurIPS","author":"Ho","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"article-title":"Training generative adversarial networks with limited data","volume-title":"NeurIPS","author":"Karras","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"article-title":"U-gat-it: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation","volume-title":"ICLR","author":"Kim","key":"ref31"},{"article-title":"Learning to discover cross-domain relations with generative adversarial networks","volume-title":"ICML","author":"Kim","key":"ref32"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma","key":"ref33"},{"article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"NeurIPS","author":"Kingma","key":"ref34"},{"article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma","key":"ref35"},{"article-title":"Diffwave: A versatile diffusion model for audio synthesis","year":"2020","author":"Kong","key":"ref36"},{"article-title":"Sinddm: A single image denoising diffusion model","year":"2022","author":"Kulikov","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01216"},{"article-title":"Magic3d: High-resolution text-to-3d content creation","year":"2022","author":"Lin","key":"ref42"},{"article-title":"Diffsinger: Diffusion acoustic model for singing voice synthesis","year":"2021","author":"Liu","key":"ref43"},{"article-title":"Unsupervised image-to-image translation networks","volume-title":"NeurIPS","author":"Liu","key":"ref44"},{"article-title":"Coupled generative adversarial networks","volume-title":"NeurIPS","author":"Liu","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"ICLR","author":"Meng","key":"ref47"},{"article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","year":"2021","author":"Nichol","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_19"},{"article-title":"Scalable diffusion models with transformers","year":"2022","author":"Peebles","key":"ref50"},{"article-title":"Dreamfusion: Text-to-3d using 2d diffusion","year":"2022","author":"Poole","key":"ref51"},{"article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30671-7_3"},{"article-title":"Image superresolution via iterative refinement","volume-title":"TPAMI","author":"Saharia","key":"ref55"},{"article-title":"Projected gans converge faster","volume-title":"NeurIPS","author":"Sauer","key":"ref56"},{"article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein","key":"ref57"},{"article-title":"Denoising diffusion implicit models","year":"2020","author":"Song","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"ICML","author":"Tan","key":"ref60"},{"article-title":"Human motion diffusion model","year":"2022","author":"Tevet","key":"ref61"},{"article-title":"Score-based generative modeling in latent space","volume-title":"NeurIPS","author":"Vahdat","key":"ref62"},{"article-title":"Sindiffusion: Learning a diffusion model from a single natural image","year":"2022","author":"Wang","key":"ref63"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_5"},{"article-title":"Diffusion-gan: Training gans with diffusion","year":"2022","author":"Wang","key":"ref65"},{"article-title":"Unifying diffusion models\u2019 latent space, with applications to cyclediffusion and guidance","year":"2022","author":"Wu","key":"ref66"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00820"},{"article-title":"Tackling the generative learning trilemma with denoising diffusion gans","volume-title":"ICLR","author":"Xiao","key":"ref68"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00632"},{"article-title":"Learning from multi-domain artistic images for arbitrary style transfer","year":"2018","author":"Xu","key":"ref70"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref72","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-11018-5_32","article-title":"Multi-style generative network for real-time transfer","volume-title":"ECCVW","author":"Zhang"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.13.026507"},{"article-title":"Egsde: Unpaired image-to-image translation via energy-guided stochastic differential equations","volume-title":"NeurIPS","author":"Zhao","key":"ref74"},{"article-title":"Differentiable augmentation for data-efficient gan training","volume-title":"NeurIPS","author":"Zhao","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"article-title":"Toward multimodal image-to-image translation","volume-title":"NeurIPS","author":"Zhu","key":"ref77"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","start":{"date-parts":[[2024,6,17]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2024,6,18]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10677511\/10677844\/10678380.pdf?arnumber=10678380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T04:05:47Z","timestamp":1727582747000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10678380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,17]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/cvprw63382.2024.00118","relation":{},"subject":[],"published":{"date-parts":[[2024,6,17]]}}}