{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T05:04:02Z","timestamp":1779771842832,"version":"3.53.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62525103"],"award-info":[{"award-number":["62525103"]}],"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":["62441235"],"award-info":[{"award-number":["62441235"]}],"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":["62021002"],"award-info":[{"award-number":["62021002"]}],"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":["62571294"],"award-info":[{"award-number":["62571294"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L252009"],"award-info":[{"award-number":["L252009"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"OPPO Research Fund"},{"name":"CCF-DiDi GAIA Collaborative Research Funds"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3654407","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T20:50:41Z","timestamp":1768596641000},"page":"3838-3852","source":"Crossref","is-referenced-by-count":2,"title":["LLMI3D: MLLM-Based 3D Perception From a Single 2D Image"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5810-9226","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"first","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5843-6411","authenticated-orcid":false,"given":"Sicheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"OPPO AI Center, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4180-5801","authenticated-orcid":false,"given":"Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Lu","sequence":"additional","affiliation":[{"name":"OPPO AI Center, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0137-9975","authenticated-orcid":false,"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3428317"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3285441"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02170-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3304054"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3233251"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171102"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.597"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018851"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3294820"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28525"},{"key":"ref15","article-title":"DeepSeek-Vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024"},{"key":"ref16","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"key":"ref17","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref18","article-title":"Qwen2.5-Vl","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521785"},{"key":"ref20","first-page":"1","article-title":"LoRa: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref21","article-title":"Qwen2-Vl: Enhancing vision-language models perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref25","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":"ref26","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref27","first-page":"61501","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref29","article-title":"MiniGPT-V2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02561"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00365"},{"key":"ref32","article-title":"Language-image models with 3D understanding","author":"Cho","year":"2024"},{"key":"ref33","article-title":"EMMA: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161442"},{"key":"ref36","article-title":"Ground plane matters: Picking up ground plane prior in monocular 3D object detection","author":"Yang","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00976"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126894"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","article-title":"Next-Chat: An LMM for Chat, Detection and Segmentation","author":"Zhang","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342025"},{"key":"ref46","first-page":"11966","article-title":"A convnet for the 2020 s","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Liu","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref48","article-title":"Qwen-Vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3637265"},{"key":"ref55","article-title":"GPT-4o: The cutting-edge advancement in multimodal LLM","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"ref58","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% * ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28467"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref62","article-title":"Depth Pro: Sharp monocular metric depth in less than a second","author":"Bochkovskii","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11353913.pdf?arnumber=11353913","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T04:27:41Z","timestamp":1779769661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353913\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3654407","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}