{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:10:24Z","timestamp":1787011824569,"version":"build-2736575974"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3406535","type":"journal-article","created":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T14:15:49Z","timestamp":1716905749000},"page":"78161-78172","source":"Crossref","is-referenced-by-count":22,"title":["Latent Denoising Diffusion GAN: Faster Sampling, Higher Image Quality"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3678-8541","authenticated-orcid":false,"given":"Luan Thanh","family":"Trinh","sequence":"first","affiliation":[{"name":"Department of Mathematics, Physics, Electrical Engineering and Computer Science, Yokohama National University, Yokohama, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2649-3777","authenticated-orcid":false,"given":"Tomoki","family":"Hamagami","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Physics, Electrical Engineering and Computer Science, Yokohama National University, Yokohama, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref2","article-title":"Photorealistic textto- image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv:2205.11487"},{"key":"ref3","first-page":"22863","article-title":"A variational perspective on diffusion-based generative models and score matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Huang"},{"key":"ref4","first-page":"21696","article-title":"Variational diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kingma"},{"key":"ref5","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref7","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv:2108.01073"},{"key":"ref8","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref9","article-title":"EGSDE: Unpaired image-to-image translation via energy-guided stochastic differential equations","author":"Zhao","year":"2022","journal-title":"arXiv:2207.06635"},{"key":"ref10","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2204.03458"},{"key":"ref11","article-title":"DreamFusion: Textto- 3D using 2D diffusion","author":"Poole","year":"2022","journal-title":"arXiv:2209.14988"},{"key":"ref12","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014","journal-title":"arXiv:1406.2661"},{"key":"ref13","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref14","article-title":"NICE: Non-linear independent components estimation","author":"Dinh","year":"2014","journal-title":"arXiv:1410.8516"},{"key":"ref15","article-title":"Density estimation using real NVP","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Dinh"},{"key":"ref16","article-title":"Wasserstein GAN","author":"Arjovsky","year":"2017","journal-title":"arXiv:1701.07875"},{"key":"ref17","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018","journal-title":"arXiv:1809.11096"},{"key":"ref18","article-title":"Improved training of Wasserstein GANs","author":"Gulrajani","year":"2017","journal-title":"arXiv:1704.00028"},{"key":"ref19","article-title":"Which training methods for GANs do actually converge?","author":"Mescheder","year":"2018","journal-title":"arXiv:1801.04406"},{"key":"ref20","article-title":"Unrolled generative adversarial networks","author":"Metz","year":"2017","journal-title":"arXiv:1611.02163"},{"key":"ref21","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021","journal-title":"arXiv:2105.05233"},{"key":"ref22","article-title":"Noise estimation for generative diffusion models","author":"San-Roman","year":"2021","journal-title":"arXiv:2104.02600"},{"key":"ref23","article-title":"Gotta go fast when generating data with score-based models","author":"Jolicoeur-Martineau","year":"2021","journal-title":"arXiv:2105.14080"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref25","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref26","first-page":"403","article-title":"On the theory of stochastic processes, with particular reference to applications","volume-title":"Proc. 1st Berkeley Symp. Math. Statist. Probab.","author":"Feller"},{"key":"ref27","article-title":"Analytic-DPM: An analytic estimate of the optimal reverse variance in diffusion probabilistic models","author":"Bao","year":"2022","journal-title":"arXiv:2201.06503"},{"key":"ref28","article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xiao"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00983"},{"key":"ref30","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2021","journal-title":"arXiv:2112.10752"},{"key":"ref31","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. 31st Int. Conf. Int. Conf. Mach. Learn. (ICML)","author":"Jimenez Rezende"},{"issue":"4","key":"ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592450","article-title":"Blended latent diffusion","volume":"42","author":"Avarahami","year":"2022","journal-title":"ACM Trans. Graph."},{"key":"ref33","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref34","article-title":"Taming transformers for highresolution image synthesis","author":"Esser","year":"2012","journal-title":"arXiv:2012.09841"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref36","article-title":"Vector-quantized image modeling with improved VQGAN","author":"Yu","year":"2021","journal-title":"arXiv:2110.04627"},{"key":"ref37","first-page":"658","article-title":"Generating images with perceptual similarity metrics based on deep networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dosovitskiy"},{"key":"ref38","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"Karras","year":"2018","journal-title":"arXiv:1710.10196"},{"key":"ref39","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015","journal-title":"arXiv:1506.03365"},{"key":"ref40","first-page":"30","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref41","article-title":"Improved precision and recall metric for assessing generative models","author":"Kynk\u00e4\u00e4nniemi","year":"2019","journal-title":"arXiv:1904.06991"},{"key":"ref42","article-title":"Assessing generative models via precision and recall","author":"Sajjadi","year":"2018","journal-title":"arXiv:1806.00035"},{"key":"ref43","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"arXiv:1907.05600"},{"key":"ref44","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref46","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref47","article-title":"Adversarial score matching and improved sampling for image generation","author":"Jolicoeur-Martineau","year":"2021","journal-title":"arXiv:2009.05475"},{"key":"ref48","article-title":"Maximum likelihood training of score-based diffusion models","author":"Song","year":"2021","journal-title":"arXiv:2101.09258"},{"key":"ref49","article-title":"Score-based generative modeling in latent space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref50","volume-title":"Elements of Information Theory","author":"Cover","year":"1991"},{"key":"ref51","article-title":"Notes on Kullback\u2013Leibler divergence and likelihood","author":"Shlens","year":"2014","journal-title":"arXiv:1404.2000"},{"key":"ref52","article-title":"On fast sampling of diffusion probabilistic models","author":"Kong","year":"2021","journal-title":"arXiv:2106.00132"},{"key":"ref53","article-title":"Learning energy-based models by diffusion recovery likelihood","author":"Gao","year":"2021","journal-title":"arXiv:2012.08125"},{"key":"ref54","article-title":"Knowledge distillation in iterative generative models for improved sampling speed","author":"Luhman","year":"2021","journal-title":"arXiv:2101.02388"},{"key":"ref55","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2018","journal-title":"arXiv:1802.05957"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00332"},{"key":"ref57","article-title":"Training generative adversarial networks with limited data","author":"Karras","year":"2020","journal-title":"arXiv:2006.06676"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref59","article-title":"Glow: Generative flowwith invertible 1\u00d71 convolutions","author":"Kingma","year":"2018","journal-title":"arXiv:1807.03039"},{"key":"ref60","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"van den Oord"},{"key":"ref61","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref62","article-title":"VAEBM: A symbiosis between variational autoencoders and energy-based models","author":"Xiao","year":"2021","journal-title":"arXiv:2010.00654"},{"key":"ref63","first-page":"3518","article-title":"Imagebart: Bidirectional context with multinomial diffusion for autoregressive image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Esser"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01405"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref66","article-title":"One-step diffusion with distribution matching distillation","author":"Yin","year":"2023","journal-title":"arXiv:2311.18828"},{"key":"ref67","article-title":"Adversarial diffusion distillation","author":"Sauer","year":"2023","journal-title":"arXiv:2311.17042"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10540088.pdf?arnumber=10540088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T17:02:45Z","timestamp":1719334965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10540088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3406535","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}