{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:20Z","timestamp":1777890140443,"version":"3.51.4"},"reference-count":44,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01667","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17941-17950","source":"Crossref","is-referenced-by-count":0,"title":["InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis"],"prefix":"10.1109","author":[{"given":"Tao","family":"Han","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanghan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junchao","family":"Gong","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Yue","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luping","family":"Zhou","sequence":"additional","affiliation":[{"name":"The University of Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Bai","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02117"},{"key":"ref8","article-title":"Scalecrafter: Tuning-free higherresolution visual generation with diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"He","year":"2023"},{"key":"ref9","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"},{"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":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_12"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3103"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref15","article-title":"Auto-encoding variational bayes","volume-title":"International Conference on Learning Representations","author":"Kingma","year":"2014"},{"key":"ref16","article-title":"Improved precision and recall metric for assessing generative models","volume":"32","author":"Kynk\u00e4\u00e4nniemi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref18","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"Fit: Flexible vision transformer for diffusion model","volume-title":"ICML","author":"Lu","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref21","article-title":"images with sparse representations","author":"Nash","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref24","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"issue":"2","key":"ref25","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref27","article-title":"Ultrapixel: Advancing ultra-high-resolution image synthesis to new peaks","volume-title":"NeurIPs","author":"Ren","year":"2024"},{"key":"ref28","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"International conference on machine learning","author":"Jimenez Rezende","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.09661"},{"key":"ref33","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref34","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref38","article-title":"Exploring representation-aligned latent space for better generation","author":"Xu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_9"},{"key":"ref40","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00475"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref44","article-title":"Fast training of diffusion models with masked transformers","author":"Zheng","year":"2024","journal-title":"Transactions on Machine Learning Research (TMLR)"}],"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\/11445260.pdf?arnumber=11445260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:51Z","timestamp":1777613511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01667","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}