{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:13:47Z","timestamp":1777889627252,"version":"3.51.4"},"reference-count":62,"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\/iccv51701.2025.01596","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17181-17190","source":"Crossref","is-referenced-by-count":0,"title":["Spectral Image Tokenizer"],"prefix":"10.1109","author":[{"given":"Carlos","family":"Esteves","sequence":"first","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed","family":"Suhail","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ameesh","family":"Makadia","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Improving image generation with better captions","author":"Betker"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975673.71"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref4","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"ICML"},{"key":"ref5","article-title":"PixelSNAIL: An improved autoregressive generative model","author":"Chen","year":"2018","journal-title":"ICML"},{"key":"ref6","volume-title":"Pali: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/357744.357757"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160450502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970104"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","volume-title":"Diffusion is spectral autoregression","author":"Dieleman","year":"2024"},{"key":"ref13","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref14","volume-title":"Quantised global autoencoder: A holistic approach to representing visual data","author":"Elsner","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref16","author":"Esser","year":"2024","journal-title":"Scaling rectified flow transformers for high-resolution image synthesis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459836"},{"key":"ref18","article-title":"Matryoshka diffusion models","author":"Gu","year":"2024","journal-title":"ICLR"},{"key":"ref19","volume-title":"Learnings from scaling visual tokenizers for reconstruction and generation","author":"Hansen-Estruch","year":"2025"},{"key":"ref20","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref21","volume-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02164"},{"key":"ref23","volume-title":"Imagen-Team-Google","year":"2024"},{"key":"ref24","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"Karras","year":"2018","journal-title":"ICLR"},{"key":"ref25","first-page":"17920","article-title":"Sinddm: A single image denoising diffusion model","author":"Kulikov","year":"2023","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","volume-title":"Star: Scale-wise text-toimage generation via auto-regressive representations","author":"Ma","year":"2024"},{"key":"ref29","article-title":"A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way","author":"Mallat","year":"2008","journal-title":"Academic Press, Inc., USA, 3rd edition"},{"key":"ref30","volume-title":"Wavelets are all you need for autoregressive image generation","author":"Mattar","year":"2024"},{"key":"ref31","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2018","journal-title":"ICLR"},{"key":"ref32","article-title":"Generating images with sparse representations","author":"Nash","year":"2021","journal-title":"ICML"},{"key":"ref33","volume-title":"OpenAI. Gpt-4 technical report","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00983"},{"key":"ref36","volume-title":"When worse is better: Navigating the compression-generation tradeoff in visual tokenization","author":"Ramanujan","year":"2024"},{"key":"ref37","article-title":"Generating diverse high-fidelity images with vq-vae-2","author":"Razavi","year":"2019","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00467"},{"key":"ref40","volume-title":"Pyramidal denoising diffusion probabilistic models","author":"Ryu","year":"2022"},{"key":"ref41","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref42","volume-title":"Glu variants improve transformer","author":"Shazeer","year":"2020"},{"key":"ref43","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref45","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.51644\/9781771120920-031"},{"key":"ref47","volume-title":"The llama 3 herd of models","year":"2024"},{"key":"ref48","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"NeurIPS"},{"key":"ref49","article-title":"Conditional image generation with pixelcnn decoders","author":"van den Oord","year":"2016","journal-title":"NeurIPS"},{"key":"ref50","article-title":"Pixel recurrent neural networks","author":"Oord","year":"2016","journal-title":"ICML"},{"key":"ref51","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref52","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref53","article-title":"principal components","author":"Wen","year":"2025","journal-title":"enable a new language of images"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_19"},{"key":"ref56","volume-title":"Frequency autoregressive image generation with continuous tokens","author":"Yu","year":"2025"},{"key":"ref57","article-title":"Vector-quantized image modeling with improved VQGAN","author":"Yu","year":"2022","journal-title":"ICLR"},{"key":"ref58","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref59","article-title":"Language model beats diffusion - tokenizer is key to visual generation","author":"Yu","year":"2024","journal-title":"ICLR"},{"key":"ref60","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref62","volume-title":"Wavelet-based image tokenizer for vision transformers","author":"Zhu","year":"2024"}],"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\/11443527.pdf?arnumber=11443527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:05Z","timestamp":1777612445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01596","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}