{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:50:31Z","timestamp":1781585431493,"version":"3.54.5"},"reference-count":88,"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\/iccv51701.2025.00488","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-12","source":"Crossref","is-referenced-by-count":3,"title":["TAR3D: Creating High-Quality 3D Assets Via Next-Part Prediction"],"prefix":"10.1109","author":[{"given":"Xuying","family":"Zhang","sequence":"first","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutong","family":"Liu","sequence":"additional","affiliation":[{"name":"USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangguang","family":"Li","sequence":"additional","affiliation":[{"name":"CUHK MMLab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Renrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"CUHK MMLab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[{"name":"CUHK MMLab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Xiong","sequence":"additional","affiliation":[{"name":"USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"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","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"16123","article-title":"Efficient geometry-aware 3d generative adversarial networks","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Eric"},{"key":"ref6","article-title":"Shapenet: An information-rich 3d model repository","author":"Angel","year":"2015","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3080"},{"key":"ref9","first-page":"32","article-title":"Learning to predict 3d objects with an interpolation-based differentiable renderer","author":"Chen","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_18"},{"key":"ref11","article-title":"Meshanything: Artist-created mesh generation with autoregressive transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Region-aware text-to-image generation via hard binding and soft refinement","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02475"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"issue":"70","key":"ref16","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref18","first-page":"36","article-title":"Objaverse-xl: A universe of $10 ~\\mathrm{m}+3 ~\\mathrm{d}$ objects","author":"Deitke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"31","article-title":"The challenge of realistic music generation: modelling raw audio at scale","author":"Dieleman","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01534-z"},{"key":"ref24","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","author":"He","year":"2023","journal-title":"Openlrm: Open-source large reconstruction models"},{"key":"ref26","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu"},{"key":"ref29","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3523675"},{"key":"ref31","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_7"},{"key":"ref34","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"12642","article-title":"Diffusionsdf: Text-to-shape via voxelized diffusion","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680994"},{"key":"ref38","first-page":"36","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"Meshformer: High-quality mesh generation with 3d-guided reconstruction model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","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":"ref41","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687621"},{"key":"ref43","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02324"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref49","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref51","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref52","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref55","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00042-1"},{"key":"ref59","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1498-0"},{"key":"ref61","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","author":"Tancik","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref63","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","first-page":"30","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3583795"},{"key":"ref67","article-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"ref69","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref71","first-page":"29","article-title":"Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling","author":"Wu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref72","article-title":"Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","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"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0321-5"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"issue":"3","key":"ref76","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"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1590"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref79","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_15"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01847"},{"key":"ref85","article-title":"Ar-1-to-3: Single image to consistent 3d object generation via next-view prediction","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref86","first-page":"36","article-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref87","article-title":"GS-ROR: 3D Gaussian splatting for reflective object relighting via sdf priors","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02333"}],"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\/11444449.pdf?arnumber=11444449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:33Z","timestamp":1777611993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00488","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}