{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:22:14Z","timestamp":1782318134186,"version":"3.54.5"},"reference-count":77,"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\/iccv51701.2025.02438","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26273-26283","source":"Crossref","is-referenced-by-count":3,"title":["AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction"],"prefix":"10.1109","author":[{"given":"Xuying","family":"Zhang","sequence":"first","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yupeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yikai","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaohui","family":"Jiao","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daquan","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qibin","family":"Hou","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0759"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3080"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_18"},{"key":"ref5","article-title":"Meshanything: Artist-created mesh generation with autoregressive transformers","author":"Chen","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02642"},{"key":"ref7","article-title":"Region-aware text-to-image generation via hard binding and soft refinement","author":"Chen","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref8","article-title":"Adaptive guidance learning for camouflaged object detection","author":"Chen","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref11","article-title":"Textcrafter: Accurately rendering multiple texts in complex visual scenes","author":"Du","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref13","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref14","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","author":"Han","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00926"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3523675"},{"key":"ref19","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref20","volume-title":"Flux","year":"2024"},{"key":"ref21","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref22","article-title":"Dual3d: Efficient and consistent text-to-3d generation with dual-mode multi-view latent diffusion","author":"Li","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2391"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref26","article-title":"Atprompt: Textual prompt learning with embedded attributes","author":"Li","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680994"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref29","article-title":"One-2-3-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref31","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref33","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arxiv preprint arxiv"},{"key":"ref34","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1491-7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0337-5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref39","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref40","article-title":"Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors","author":"Qian","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730600"},{"key":"ref42","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","article-title":"Rolling diffusion models","author":"Ruhe","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref45","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref46","article-title":"Convolutional 1stm network: A machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref47","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref49","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref51","article-title":"Mvdiffusion: Enabling holistic multiview image generation with correspondence-aware diffusion","author":"Tang","year":"2023","journal-title":"arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32787"},{"key":"ref53","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref54","article-title":"Triposr: Fast 3d object reconstruction from a single image","author":"Tochilkin","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref55","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"International conference on machine learning","author":"Van Den Oord","year":"2016"},{"key":"ref56","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref57","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3583795"},{"key":"ref60","article-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation","author":"Wang","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref62","article-title":"Unique3d: High-quality and efficient 3d mesh generation from a single image","author":"Wu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1360\/SSI-2024-0295"},{"key":"ref65","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"arxiv preprint arxiv"},{"issue":"3","key":"ref66","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2","author":"Yu","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref67","volume-title":"Reference-only control","author":"Zhang","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_15"},{"key":"ref70","article-title":"Tar3d: Creating high-quality 3d assets via next-part prediction","author":"Zhang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01847"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3236"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00928"},{"key":"ref74","article-title":"Storydiffusion: Consistent selfattention for long-range image and video generation","author":"Zhou","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref75","article-title":"GS-ROR: 3D Gaussian splatting for reflective object relighting via sdf priors","author":"Zhu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02333"},{"key":"ref77","volume-title":"Videomv: Consistent multiview generation based on large video generative model","author":"Zuo","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\/11444532.pdf?arnumber=11444532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:25Z","timestamp":1777529905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02438","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}