{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T18:10:09Z","timestamp":1749751809433,"version":"3.41.0"},"reference-count":65,"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 Science and Technology Council","award":["NSTC 113-2640-E-002-003","NSTC 113-2634-F-002-005"],"award-info":[{"award-number":["NSTC 113-2640-E-002-003","NSTC 113-2634-F-002-005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535325","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:54:42Z","timestamp":1738004082000},"page":"3294-3306","source":"Crossref","is-referenced-by-count":0,"title":["Learning Shape-Color Diffusion Priors for Text-Guided 3D Object Generation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3149-9620","authenticated-orcid":false,"given":"Sheng-Yu","family":"Huang","sequence":"first","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7738-3054","authenticated-orcid":false,"given":"Chi-Pin","family":"Huang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5182-2019","authenticated-orcid":false,"given":"Kai-Po","family":"Chang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}]},{"given":"Zi-Ting","family":"Chou","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0155-6608","authenticated-orcid":false,"given":"I-Jieh","family":"Liu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2333-157X","authenticated-orcid":false,"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01227"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355647"},{"key":"ref3","first-page":"33934","article-title":"SPoVT: Semantic-prototype variational transformer for dense point cloud semantic completion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3318327"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00378"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00395"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3340892"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2993962"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251697"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_7"},{"article-title":"Implicit maximum likelihood estimation","year":"2018","author":"Li","key":"ref13"},{"key":"ref14","first-page":"8882","article-title":"ShapeCrafter: A recursive text-conditioned 3D shape generation model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fu","year":"2022"},{"key":"ref15","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01737"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gong","year":"2023"},{"key":"ref19","article-title":"The curious case of neural text degeneration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Holtzman","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"ref21","first-page":"6480","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25133"},{"key":"ref24","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365171.2337"},{"key":"ref27","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Poole","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"article-title":"LLaMA: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref32","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"article-title":"ShapeNet: An information-rich 3D model repository","year":"2015","author":"Chang","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207181"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"den Oord","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612489"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref45","article-title":"MVDream: Multi-view diffusion for 3D generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"article-title":"Point-E: A system for generating 3D point clouds from complex prompts","year":"2022","author":"Nichol","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_17"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00842"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01305"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref55","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.2312\/LocalChapterEvents\/ItalChap\/ItalianChapConf2008\/129-136"},{"key":"ref57","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref58","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":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00396"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00088"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"article-title":"GPT-4 technical report","year":"2023","author":"Achiam","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1162"},{"issue":"8","key":"ref64","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"article-title":"OPT: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref65"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10855435.pdf?arnumber=10855435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T17:43:34Z","timestamp":1749750214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10855435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535325","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}