{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:21:00Z","timestamp":1784737260467,"version":"3.55.0"},"reference-count":48,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82371112,623B2001"],"award-info":[{"award-number":["82371112,623B2001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["Z210008"],"award-info":[{"award-number":["Z210008"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["PKU2025PKULCXQ008"],"award-info":[{"award-number":["PKU2025PKULCXQ008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00246","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2556-2566","source":"Crossref","is-referenced-by-count":1,"title":["Auto-Regressively Generating Multi-View Consistent Images"],"prefix":"10.1109","author":[{"given":"JiaKui","family":"Hu","sequence":"first","affiliation":[{"name":"Institute of Medical Technology, Peking University Health Science Center, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiao","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialun","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu VIS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinbo","family":"Wu","sequence":"additional","affiliation":[{"name":"Baidu VIS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Baidu VIS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanye","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Medical Technology, Peking University Health Science Center, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","author":"Barratt","year":"2018","journal-title":"A note on the inception score"},{"key":"ref3","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Reversible column networks","volume-title":"The Eleventh International Conference on Learning Representations","author":"Cai"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"70","key":"ref7","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01467"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref13","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":"ref14","article-title":"Universal image restoration pre-training via degradation classification","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Hu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00956"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1780"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589083"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00410"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02474"},{"key":"ref21","first-page":"9298","article-title":"Zero-1-to3: Zero-shot one image to 3d object","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Liu"},{"key":"ref22","author":"Liu","year":"2023","journal-title":"Syncdreamer: Generating multiview-consistent images from a single-view image"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00835"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3291"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00816"},{"key":"ref27","first-page":"7220","article-title":"Polygen: An autoregressive generative model of 3d meshes","volume-title":"International conference on machine learning","author":"Nash"},{"key":"ref28","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref30","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591503"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","author":"Shazeer","year":"2020","journal-title":"Glu variants improve transformer"},{"key":"ref35","author":"Shi","year":"2023","journal-title":"Zero123++: a single image to consistent multi-view diffusion base model"},{"key":"ref36","author":"Shi","year":"2023","journal-title":"Mvdream: Multi-view diffusion for 3d generation"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref38","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation"},{"key":"ref39","first-page":"84839","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","volume":"37","author":"Tian","year":"2025","journal-title":"Advances in neural information processing systems"},{"key":"ref40","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref41","article-title":"Conditional image generation with pixelcnn decoders","volume":"29","author":"Van den Oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00060"},{"key":"ref45","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3236"},{"key":"ref48","author":"Zuo","year":"2024","journal-title":"Videomv: Consistent multi-view generation based on large video generative model"}],"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\/11443474.pdf?arnumber=11443474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:05Z","timestamp":1777530185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00246","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}