{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T18:07:44Z","timestamp":1778782064992,"version":"3.51.4"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR2024MF144"],"award-info":[{"award-number":["ZR2024MF144"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273213"],"award-info":[{"award-number":["62273213"]}],"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":["62472262"],"award-info":[{"award-number":["62472262"]}],"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":["62572287"],"award-info":[{"award-number":["62572287"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.engappai.2026.114646","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T09:12:52Z","timestamp":1774861972000},"page":"114646","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Progressive contour guidance and enhanced three-dimensional prior for consistent text-to-three-dimensional generation"],"prefix":"10.1016","volume":"175","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6495-0867","authenticated-orcid":false,"given":"Honghao","family":"Liu","sequence":"first","affiliation":[]},{"given":"Haixia","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiao","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3290-6849","authenticated-orcid":false,"given":"Zhiguo","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114646_b1","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., Jia, K., 2023. Fantasia3D: Disentangling geometry and appearance for high-quality text-to-3d content creation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 22246\u201322256.","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"10.1016\/j.engappai.2026.114646_b2","series-title":"Computer Vision\u2013ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2\u20136, 2018, Revised Selected Papers, Part III 14","first-page":"100","article-title":"Text2shape: Generating shapes from natural language by learning joint embeddings","author":"Chen","year":"2019"},{"key":"10.1016\/j.engappai.2026.114646_b3","doi-asserted-by":"crossref","unstructured":"Cheng, Y.-C., Lee, H.-Y., Tulyakov, S., Schwing, A.G., Gui, L.-Y., 2023. SDFusion: Multimodal 3d shape completion, reconstruction, and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4456\u20134465.","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"10.1016\/j.engappai.2026.114646_b4","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":"10.1016\/j.engappai.2026.114646_b5","series-title":"Threestudio: A unified framework for 3D content generation","author":"Guo","year":"2023"},{"key":"10.1016\/j.engappai.2026.114646_b6","doi-asserted-by":"crossref","unstructured":"Hong, Y., Zhang, K., Gu, J., Bi, S., Zhou, Y., Liu, D., Liu, F., Sunkavalli, K., Bui, T., Tan, H., 2024. LRM: Large Reconstruction Model for Single Image to 3D. In: The Twelfth International Conference on Learning Representations.","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"10.1016\/j.engappai.2026.114646_b7","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume":"vol. 1","author":"Hu","year":"2022"},{"key":"10.1016\/j.engappai.2026.114646_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111417","article-title":"Three-dimensional reconstruction image generation of traditional Chinese painting elements","volume":"158","author":"Hu","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114646_b9","doi-asserted-by":"crossref","unstructured":"Hu, Z., Zhao, M., Zhao, C., Liang, X., Li, L., Zhao, Z., Fan, C., Zhou, X., Yu, X., 2024. EfficientDreamer: high-fidelity and robust 3d creation via orthogonal-view diffusion priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4949\u20134958.","DOI":"10.1109\/CVPR52733.2024.00473"},{"key":"10.1016\/j.engappai.2026.114646_b10","series-title":"MV-Adapter: Multi-view consistent image generation made easy","author":"Huang","year":"2024"},{"key":"10.1016\/j.engappai.2026.114646_b11","doi-asserted-by":"crossref","unstructured":"Huang, T., Zeng, Y., Zhang, Z., Xu, W., Xu, H., Xu, S., Lau, R.W., Zuo, W., 2024. DreamControl: Control-based text-to-3d generation with 3d self-prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5364\u20135373.","DOI":"10.1109\/CVPR52733.2024.00513"},{"key":"10.1016\/j.engappai.2026.114646_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110305","article-title":"High-quality three-dimensional cartoon avatar reconstruction with Gaussian splatting","volume":"148","author":"Jang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114646_b13","series-title":"Shap-E: Generating conditional 3d implicit functions","author":"Jun","year":"2023"},{"key":"10.1016\/j.engappai.2026.114646_b14","doi-asserted-by":"crossref","first-page":"36652","DOI":"10.52202\/075280-1594","article-title":"Pick-a-Pic: An open dataset of user preferences for text-to-image generation","volume":"36","author":"Kirstain","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114646_b15","series-title":"SweetDreamer: Aligning geometric priors in 2d diffusion for consistent text-to-3d","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.114646_b16","series-title":"MVControl: Adding conditional control to multi-view diffusion for controllable text-to-3d generation","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.114646_b17","doi-asserted-by":"crossref","unstructured":"Lin, C.-H., Gao, J., Tang, L., Takikawa, T., Zeng, X., Huang, X., Kreis, K., Fidler, S., Liu, M.-Y., Lin, T.-Y., 2023. Magic3D: High-resolution text-to-3d content creation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 300\u2013309.","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"10.1016\/j.engappai.2026.114646_b18","unstructured":"Liu, Y., Lin, C., Zeng, Z., Long, X., Liu, L., Komura, T., Wang, W., 2023. SyncDreamer: Generating Multiview-consistent Images from a Single-view Image. In: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.114646_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111909","article-title":"An approach to optimizing semantic consistency for text-to-digital human generation","volume":"160","author":"Liu","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114646_b20","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C., 2023. Zero-1-to-3: Zero-shot one image to 3d object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9298\u20139309.","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"10.1016\/j.engappai.2026.114646_b21","doi-asserted-by":"crossref","unstructured":"Long, X., Guo, Y.-C., Lin, C., Liu, Y., Dou, Z., Liu, L., Ma, Y., Zhang, S.-H., Habermann, M., Theobalt, C., et al., 2024. Wonder3D: Single image to 3d using cross-domain diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9970\u20139980.","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"10.1016\/j.engappai.2026.114646_b22","doi-asserted-by":"crossref","unstructured":"Michel, O., Bar-On, R., Liu, R., Benaim, S., Hanocka, R., 2022. Text2Mesh: Text-driven neural stylization for meshes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13492\u201313502.","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"10.1016\/j.engappai.2026.114646_b23","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R., 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In: European Conference on Computer Vision. pp. 405\u2013421.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"10.1016\/j.engappai.2026.114646_b24","doi-asserted-by":"crossref","unstructured":"Mohammad Khalid, N., Xie, T., Belilovsky, E., Popa, T., 2022. CLIP-Mesh: Generating textured meshes from text using pretrained image-text models. In: SIGGRAPH Asia 2022 Conference Papers. pp. 1\u20138.","DOI":"10.1145\/3550469.3555392"},{"key":"10.1016\/j.engappai.2026.114646_b25","series-title":"Point-E: A system for generating 3d point clouds from complex prompts","author":"Nichol","year":"2022"},{"key":"10.1016\/j.engappai.2026.114646_b26","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B., 2022. DreamFusion: Text-to-3D using 2D Diffusion. In: The Eleventh International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.114646_b27","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.engappai.2026.114646_b28","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B., 2022. High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.engappai.2026.114646_b29","series-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023"},{"key":"10.1016\/j.engappai.2026.114646_b30","unstructured":"Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X., 2023. MVDream: Multi-view Diffusion for 3D Generation. In: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.114646_b31","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1109\/TMM.2020.2993962","article-title":"3D face reconstruction from a single image assisted by 2D face images in the wild","volume":"23","author":"Tu","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.114646_b32","doi-asserted-by":"crossref","unstructured":"Wang, C., Chai, M., He, M., Chen, D., Liao, J., 2022. CLIP-NeRF: Text-and-image driven manipulation of neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3835\u20133844.","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"10.1016\/j.engappai.2026.114646_b33","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G., 2023. Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12619\u201312629.","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"10.1016\/j.engappai.2026.114646_b34","doi-asserted-by":"crossref","first-page":"4028","DOI":"10.1109\/TMM.2021.3111485","article-title":"Prior-guided multi-view 3d head reconstruction","volume":"24","author":"Wang","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.114646_b35","first-page":"8406","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114646_b36","doi-asserted-by":"crossref","unstructured":"Xiang, J., Lv, Z., Xu, S., Deng, Y., Wang, R., Zhang, B., Chen, D., Tong, X., Yang, J., 2025. Structured 3d latents for scalable and versatile 3d generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 21469\u201321480.","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"10.1016\/j.engappai.2026.114646_b37","doi-asserted-by":"crossref","unstructured":"Xiang, J., Yang, J., Huang, B., Tong, X., 2023. 3D-aware image generation using 2d diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2383\u20132393.","DOI":"10.1109\/ICCV51070.2023.00226"},{"key":"10.1016\/j.engappai.2026.114646_b38","unstructured":"Xu, Y., Tan, H., Luan, F., Bi, S., Wang, P., Li, J., Shi, Z., Sunkavalli, K., Wetzstein, G., Xu, Z., et al., 2024. DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model. In: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.114646_b39","series-title":"BoostDream: efficient refining for high-quality text-to-3D generation from multi-view diffusion","author":"Yu","year":"2024"},{"key":"10.1016\/j.engappai.2026.114646_b40","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M., 2023. Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3836\u20133847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"10.1016\/j.engappai.2026.114646_b41","series-title":"MuMA: 3D PBR texturing via multi-channel multi-view generation and agentic post-processing","author":"Zhu","year":"2025"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626009280?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626009280?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:11:14Z","timestamp":1778778674000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626009280"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":41,"alternative-id":["S0952197626009280"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114646","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Progressive contour guidance and enhanced three-dimensional prior for consistent text-to-three-dimensional generation","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114646","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114646"}}