{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:28:10Z","timestamp":1784399290942,"version":"3.55.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0160101"],"award-info":[{"award-number":["2022ZD0160101"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071127"],"award-info":[{"award-number":["62071127"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101137"],"award-info":[{"award-number":["62101137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["23ZR1402900"],"award-info":[{"award-number":["23ZR1402900"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535389","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T13:54:42Z","timestamp":1737986082000},"page":"4107-4120","source":"Crossref","is-referenced-by-count":17,"title":["ShapeGPT: 3D Shape Generation With a Unified Multi-Modal Language Model"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2623-1619","authenticated-orcid":false,"given":"Fukun","family":"Yin","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9347-1367","authenticated-orcid":false,"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4831-8418","authenticated-orcid":false,"given":"Zibo","family":"Zhao","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3867-1825","authenticated-orcid":false,"given":"Wen","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5570-2710","authenticated-orcid":false,"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0779-9818","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref4","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"1","key":"ref6","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref9","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref11","article-title":"Image as a foreign language: Beit pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref12","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"key":"ref14","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_11"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"ref17","first-page":"20067","article-title":"Motiongpt: Human motion as a foreign language","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3132724"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00850"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/heritage2030110"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00399"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3233764"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"ref24","first-page":"73969","article-title":"Michelangelo: Conditional 3D shape generation based on shape-image-text aligned latent representation","volume":"36","author":"Zhao","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00278"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00270"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957933"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413889"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_17"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00066"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381814"},{"key":"ref32","first-page":"8882","article-title":"Shapecrafter: A recursive text-conditioned 3D shape generation model","volume":"35","author":"Fu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref35","article-title":"UNIFIED-IO: A unified model for vision, language, and multi-modal tasks","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lu","year":"2022"},{"key":"ref36","article-title":"Neural discrete representation learning","volume":"30","author":"Den Oord","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref37","first-page":"20482","article-title":"3D-LLM: Injecting the 3D world into large language models","volume":"36","author":"Hong","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01420"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01242"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00046"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01294"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3169735"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"ref47","first-page":"12705","article-title":"Coordinates are not lonely-codebook prior helps implicit neural 3 d representations","volume":"35","author":"Yin","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref48","first-page":"4805","article-title":"Volume rendering of neural implicit surfaces","volume":"34","author":"Yariv","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref50","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90$^*$ ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref51","article-title":"Gpt-4 technical report","year":"2023","journal-title":"arXiv:2303.08774"},{"key":"ref52","first-page":"72096","article-title":"Language is not all you need: Aligning perception with language models","volume":"36","author":"Huang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref53","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref58","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref59","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref60","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237166"},{"key":"ref62","first-page":"32172","article-title":"HSDF: Hybrid sign and distance field for modeling surfaces with arbitrary topologies","volume":"35","author":"Wang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref63","article-title":"DISN: Deep implicit surface network for high-quality single-view 3D reconstruction","volume":"32","author":"Xu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref64","article-title":"PixelTransformer: Sample conditioned signal generation","author":"Tulsiani","year":"2021","journal-title":"arXiv:2103.15813"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.blackboxnlp-1.26"},{"key":"ref66","first-page":"38546","article-title":"Exploring length generalization in large language models","volume":"35","author":"Anil","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_7"},{"key":"ref71","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv:1512.03012[cs.GR]"},{"key":"ref72","article-title":"MOAT: Alternating mobile convolution and attention brings strong vision models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Yang","year":"2022"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/83.718487"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/11941439_114"},{"key":"ref76","article-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv:2212.08751"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00120"},{"key":"ref78","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle","year":"2021"},{"key":"ref79","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref80","article-title":"Point-bind & point-LLM: Aligning point cloud with multi-modality for 3D understanding, generation, and instruction following","author":"Guo","year":"2023","journal-title":"arXiv:2309.00615"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00407"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10855507.pdf?arnumber=10855507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:48:46Z","timestamp":1752169726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10855507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535389","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}