{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:53:49Z","timestamp":1781538829208,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Chongqing Social Science Planning Project","award":["2025PY15"],"award-info":[{"award-number":["2025PY15"]}]},{"name":"\u91cd\u5e86\u5e02\u6559\u80b2\u59d4\u5458\u4f1a\u4eba\u6587\u793e\u4f1a\u79d1\u5b66\u7efc\u5408\u9879\u76ee","award":["24SKGH077"],"award-info":[{"award-number":["24SKGH077"]}]},{"name":"Chongqing Natural Science Foundation General Project","award":["CSTB2025NSCQ-GPX1037"],"award-info":[{"award-number":["CSTB2025NSCQ-GPX1037"]}]},{"name":"Chongqing Natural Science Foundation General Project","award":["CSTB2023NSCQ-MSX0407"],"award-info":[{"award-number":["CSTB2023NSCQ-MSX0407"]}]},{"name":"Chongqing Natural Science Foundation General Project","award":["CSTB2024NSCQ-MSX0468"],"award-info":[{"award-number":["CSTB2024NSCQ-MSX0468"]}]},{"name":"Science and Technology Research Project of Chongqing Education Commission","award":["KJQN202300533"],"award-info":[{"award-number":["KJQN202300533"]}]},{"name":"Doctoral Research Project of Chongqing Normal University","award":["22XLB018"],"award-info":[{"award-number":["22XLB018"]}]},{"name":"Doctoral Research Project of Chongqing Normal University","award":["22XLB017"],"award-info":[{"award-number":["22XLB017"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810761","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"700-709","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MOC-3D: Manifold-Order Consistency for Text-to-3D Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8232-8217","authenticated-orcid":false,"given":"Chenyang","family":"Fan","sequence":"first","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0683-7958","authenticated-orcid":false,"given":"Wen","family":"Yang","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3422-2865","authenticated-orcid":false,"given":"Junshi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1547-861X","authenticated-orcid":false,"given":"Zihong","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7459-2510","authenticated-orcid":false,"given":"Wenfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4637-8995","authenticated-orcid":false,"given":"Wei","family":"Hu","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4633-1363","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6674-9749","authenticated-orcid":false,"given":"Pan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Vincent Arsigny Pierre Fillard Xavier Pennec et\u00a0al. 2006. Log-Euclidean metrics for fast and simple calculus on diffusion tensors. Magnetic Resonance in Medicine 56 2 (2006) 411\u2013421.","DOI":"10.1002\/mrm.20965"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Peter\u00a0J Basser James Mattiello and Denis LeBihan. 1994. MR diffusion tensor spectroscopy and imaging. Biophysical Journal 66 1 (1994) 259\u2013267.","DOI":"10.1016\/S0006-3495(94)80775-1"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"e_1_3_3_1_5_2","unstructured":"H. Chen B. Shen Y. Liu et\u00a0al. 2024. 3D-Adapter: Geometry-consistent multi-view diffusion for high-quality 3D generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.18974 abs\/2410.18974 1 (2024) 1\u201310."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_1_7_2","unstructured":"Z. Chen Y. Wang Z. Wang et\u00a0al. 2023. Text-to-3D using Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.16585 abs\/2309.16585 1 (2023) 1\u201310."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00489"},{"key":"e_1_3_3_1_9_2","first-page":"1","volume-title":"Proceedings of the Thirty-Eighth Conference on Neural Information Processing Systems (NeurIPS)","author":"Gao R.","year":"2024","unstructured":"R. Gao, A. Holynski, P. Henzler, et\u00a0al. 2024. CAT3D: Create Anything in 3D with Multi-View Diffusion Models. In Proceedings of the Thirty-Eighth Conference on Neural Information Processing Systems (NeurIPS). Curran Associates, Inc., Vancouver, BC, Canada, 1\u201315."},{"key":"e_1_3_3_1_10_2","first-page":"1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Gao R.","year":"2025","unstructured":"R. Gao, A. Holynski, P. Henzler, et\u00a0al. 2025. CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Nashville, TN, USA, 1\u201310."},{"key":"e_1_3_3_1_11_2","unstructured":"Y.C. Guo Y.T. Liu R. Shao et\u00a0al. 2023. Threestudio: A modular framework for diffusion-guided 3D generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.08562 abs\/2310.08562 1 (2023) 1\u201310."},{"key":"e_1_3_3_1_12_2","first-page":"1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hong Yicong","year":"2024","unstructured":"Yicong Hong, Kai Zhang, Jiatao Gu, et\u00a0al. 2024. 3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Seattle, WA, USA, 1\u201310."},{"key":"e_1_3_3_1_13_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hong Yicong","year":"2024","unstructured":"Yicong Hong, Kai Zhang, Jiatao Gu, et\u00a0al. 2024. LRM: Large Reconstruction Model for Single Image to 3D. In Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net, Vienna, Austria, 1\u201315."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02204"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01520"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10866"},{"key":"e_1_3_3_1_17_2","first-page":"12267","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Jain Ajay","year":"2021","unstructured":"Ajay Jain, Matthew Tancik, and Pieter Abbeel. 2021. DietNeRF: Monocular Neural Radiance Fields with Semantic Consistency. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE, Montreal, QC, Canada, 12267\u201312276."},{"key":"e_1_3_3_1_18_2","unstructured":"Heewoo Jun and Alex Nichol. 2023. Shap-E: Generating Conditional 3D Implicit Functions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.02463 abs\/2305.02463 1 (2023) 1\u201310."},{"key":"e_1_3_3_1_19_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Li W.","year":"2024","unstructured":"W. Li, R. Chen, X. Chen, et\u00a0al. 2024. SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Text-to-3D. In Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net, Vienna, Austria, 1\u201315."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_3_1_22_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Ma Yiwei","year":"2024","unstructured":"Yiwei Ma, Ying He, Kaushik Kundu, et\u00a0al. 2024. ScaleDreamer: A Scalable and Efficient Framework for High-Quality Text-to-3D Generation. In Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net, Vienna, Austria, 1\u201315."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Thomas M\u00fcller Alex Evans Christoph Schied et\u00a0al. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (TOG) 41 4 (2022) 102:1\u2013102:15.","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_3_1_25_2","unstructured":"Alex Nichol Heewoo Jun Prafulla Dhariwal et\u00a0al. 2022. Point-E: A System for Generating 3D Point Clouds from Complex Prompts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.08751 abs\/2212.08751 1 (2022) 1\u201310."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Xavier Pennec Pierre Fillard and Nicholas Ayache. 2006. A Riemannian framework for tensor computing. International Journal of Computer Vision 66 1 (2006) 41\u201366.","DOI":"10.1007\/s11263-005-3222-z"},{"key":"e_1_3_3_1_27_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T Barron, et\u00a0al. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net, Kigali, Rwanda, 1\u201315."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01726"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"e_1_3_3_1_30_2","first-page":"416","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Rossi Dario","year":"2022","unstructured":"Dario Rossi, Barbara Roessle, A.L. Rodriguez, et\u00a0al. 2022. PeRF: Pose-Free Neural Radiance Fields. In Proceedings of the European Conference on Computer Vision (ECCV). Springer, Tel Aviv, Israel, 416\u2013433."},{"key":"e_1_3_3_1_31_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Shi Yichun","year":"2024","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, et\u00a0al. 2024. MVDream: Multi-view Diffusion for 3D Generation. In Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net, Vienna, Austria, 1\u201315."},{"key":"e_1_3_3_1_32_2","unstructured":"Matthew Tancik Heewoo Jun et\u00a0al. 2023. TextMesh: Generation of Realistic 3D Meshes from Text Prompts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.12439 abs\/2304.12439 1 (2023) 1\u201310."},{"key":"e_1_3_3_1_33_2","first-page":"4353","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tang Jiaxiang","year":"2024","unstructured":"Jiaxiang Tang, Jiawei Ren, Hang Zhou, et\u00a0al. 2024. LGM: Large multi-view gaussian model for high-resolution 3d content creation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Seattle, WA, USA, 4353\u20134364."},{"key":"e_1_3_3_1_34_2","unstructured":"Z. Tang S. Gu C. Wang et\u00a0al. 2023. Volumediffusion: Flexible text-to-3d generation with efficient volumetric encoder. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.11459 abs\/2312.11459 1 (2023) 1\u201310."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/11744047_45"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"e_1_3_3_1_37_2","first-page":"25779","volume-title":"Proceedings of the Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS)","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yiming Wang, et\u00a0al. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. In Proceedings of the Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS). Curran Associates, Inc., New Orleans, LA, USA, 25779\u201325797."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_1_39_2","unstructured":"Z. Xu Q. Wang Y. Yang et\u00a0al. 2025. Target-Balanced Score Distillation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.11710 abs\/2511.11710 1 (2025) 1\u201310."},{"key":"e_1_3_3_1_40_2","unstructured":"X. Yang H. Shi B. Zhang et\u00a0al. 2024. Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.02293 abs\/2411.02293 1 (2024) 1\u201310."},{"key":"e_1_3_3_1_41_2","first-page":"4805","volume-title":"Proceedings of the Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS)","author":"Yariv Lior","year":"2021","unstructured":"Lior Yariv, Jiatao Gu, Yoni Kasten, et\u00a0al. 2021. Volume rendering of neural implicit surfaces. In Proceedings of the Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS). Curran Associates, Inc., Online, 4805\u20134815."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01404"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:57:42Z","timestamp":1781535462000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":42,"alternative-id":["10.1145\/3805622.3810761","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810761","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}