{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T07:37:01Z","timestamp":1774078621029,"version":"3.50.1"},"reference-count":77,"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":"crossref","award":["U23A20315"],"award-info":[{"award-number":["U23A20315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82441006"],"award-info":[{"award-number":["82441006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U22A2097"],"award-info":[{"award-number":["U22A2097"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62425208"],"award-info":[{"award-number":["62425208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402094"],"award-info":[{"award-number":["62402094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["JCYJ20240813114208012"],"award-info":[{"award-number":["JCYJ20240813114208012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3671597","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:40:22Z","timestamp":1773348022000},"page":"2955-2968","source":"Crossref","is-referenced-by-count":0,"title":["SeMv-3D: Toward Concurrency of Semantic and Multi-View Consistency in General Text-to-3D Generation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7576-9621","authenticated-orcid":false,"given":"Xiao","family":"Cai","sequence":"first","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0672-3790","authenticated-orcid":false,"given":"Pengpeng","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7406-116X","authenticated-orcid":false,"given":"Sitong","family":"Su","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Poole"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref3","first-page":"8406","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3D generation with variational score distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref6","article-title":"Instant3D: Fast text-to-3D with sparse-view generation and large reconstruction model","author":"Li","year":"2023","journal-title":"arXiv:2311.06214"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00983"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"ref10","first-page":"22226","article-title":"One-2\u20133\u201345: Any single image to 3D mesh in 45 seconds without per-shape optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref11","article-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv:2212.08751"},{"key":"ref12","article-title":"VolumeDiffusion: Flexible text-to-3D generation with efficient volumetric encoder","author":"Tang","year":"2023","journal-title":"arXiv:2312.11459"},{"key":"ref13","first-page":"1","article-title":"MVDream: Multi-view diffusion for 3D generation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Shi"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_21"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref16","article-title":"3DTopia: Large text-to-3D generation model with hybrid diffusion priors","author":"Hong","year":"2024","journal-title":"arXiv:2403.02234"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref22","first-page":"121859","article-title":"Direct3D: Scalable image-to-3D generation via 3D latent diffusion transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3279661"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3539935"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3215024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3203213"},{"key":"ref29","article-title":"Advances in 3D generation: A survey","author":"Li","year":"2024","journal-title":"arXiv:2401.17807"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01343"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3658120"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3018865"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00046"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0728"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"ref39","article-title":"Shap-E: Generating conditional 3D implicit functions","author":"Jun","year":"2023","journal-title":"arXiv:2305.02463"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02097-5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3584051"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612489"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00468"},{"key":"ref49","article-title":"StyleMe3D: Stylization with disentangled priors by multiple encoders on 3D Gaussians","author":"Zhuang","year":"2025","journal-title":"arXiv:2504.15281"},{"key":"ref50","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:2306.17843"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"ref52","article-title":"ImageDream: Image-prompt multi-view diffusion for 3D generation","author":"Wang","year":"2023","journal-title":"arXiv:2312.02201"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_10"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00154"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01645"},{"key":"ref56","article-title":"AToM: Amortized text-to-mesh using 2D diffusion","author":"Qian","year":"2024","journal-title":"arXiv:2402.00867"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0243"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i21.38848"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/87"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755516"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00934"},{"key":"ref62","first-page":"55975","article-title":"Era3D: High-resolution multiview diffusion using efficient row-wise attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681634"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00956"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00500"},{"key":"ref66","article-title":"3DGen: Triplane latent diffusion for textured mesh generation","author":"Gupta","year":"2023","journal-title":"arXiv:2303.05371"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01450"},{"key":"ref71","volume-title":"LLaVA-NeXT: Improved Reasoning, OCR, and World Knowledge","author":"Liu","year":"2024"},{"key":"ref72","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref74","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv:2303.08774"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3469579"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11433533.pdf?arnumber=11433533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T04:46:16Z","timestamp":1774068376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3671597","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}