{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T13:44:01Z","timestamp":1787579041137,"version":"build-2736575974"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"the University Research Initiation","award":["Grant 2030011540027."],"award-info":[{"award-number":["Grant 2030011540027."]}]},{"name":"the University Research Initiation","award":["Grant 2030011540027."],"award-info":[{"award-number":["Grant 2030011540027."]}]},{"name":"the University Research Initiation","award":["Grant 2030011540027."],"award-info":[{"award-number":["Grant 2030011540027."]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-24916-6","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T11:04:37Z","timestamp":1763636677000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["NeuroDiff3D: a 3D generation method optimizing viewpoint consistency through diffusion modeling"],"prefix":"10.1038","volume":"15","author":[{"given":"Kai","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Sui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"24916_CR1","unstructured":"Poole, B., Jain, A., Barron, J.\u00a0T. & Mildenhall, B. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"24916_CR2","doi-asserted-by":"crossref","unstructured":"Lin, C.-H. et al. Magic3d: High-resolution text-to-3d content creation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 300\u2013309 (2023).","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"24916_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127229","volume":"277","author":"J Li","year":"2025","unstructured":"Li, J., Wang, Y., Ning, X., He, W. & Cai, W. Fefdm-transformer: Dual-channel multi-stage transformer-based encoding and fusion mode for infrared-visible images. Expert Systems with Applications 277, 127229 (2025).","journal-title":"Expert Systems with Applications"},{"key":"24916_CR4","first-page":"1","volume":"14","author":"A Kodipalli","year":"2023","unstructured":"Kodipalli, A., Fernandes, S. L., Dasar, S. K. & Ismail, T. Computational framework of inverted fuzzy c-means and quantum convolutional neural network towards accurate detection of ovarian tumors. International Journal of E-Health and Medical Communications (IJEHMC) 14, 1\u201316 (2023).","journal-title":"International Journal of E-Health and Medical Communications (IJEHMC)"},{"key":"24916_CR5","doi-asserted-by":"crossref","unstructured":"Raj, A. et al. Dreambooth3d: Subject-driven text-to-3d generation. In Proceedings of the IEEE\/CVF international conference on computer vision, 2349\u20132359 (2023).","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"24916_CR6","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N. & Jia, K. Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation. In Proceedings of the IEEE\/CVF international conference on computer vision, 22246\u201322256 (2023).","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"24916_CR7","unstructured":"Li, J. et al. Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model. arXiv preprint arXiv:2311.06214 (2023)."},{"key":"24916_CR8","doi-asserted-by":"crossref","unstructured":"Ning, X. et al. Abm: An automatic body measurement framework via body deformation and topology-aware b-spline approximation. Pattern Recognition 112060 (2025).","DOI":"10.1016\/j.patcog.2025.112060"},{"key":"24916_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.102950","volume":"118","author":"X Xing","year":"2025","unstructured":"Xing, X., Wang, B., Ning, X., Wang, G. & Tiwari, P. Short-term od flow prediction for urban rail transit control: A multi-graph spatiotemporal fusion approach. Information Fusion 118, 102950. https:\/\/doi.org\/10.1016\/j.inffus.2025.102950 (2025).","journal-title":"Information Fusion"},{"key":"24916_CR10","doi-asserted-by":"crossref","unstructured":"Chang, A., Savva, M. & Manning, C.\u00a0D. Learning spatial knowledge for text to 3d scene generation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 2028\u20132038 (2014).","DOI":"10.3115\/v1\/D14-1217"},{"key":"24916_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129426","volume":"623","author":"J Cao","year":"2025","unstructured":"Cao, J., Zou, Q., Ning, X., Wang, Z. & Wang, G. Fipnet: Self-supervised low-light image enhancement combining feature and illumination priors. Neurocomputing 623, 129426 (2025).","journal-title":"Neurocomputing"},{"key":"24916_CR12","first-page":"29620","volume":"37","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Liu, Z., Wang, Y., Feng, B. & Li, Y. Subgdiff: A subgraph diffusion model to improve molecular representation learning. Advances in Neural Information Processing Systems 37, 29620\u201329656 (2024).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"24916_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Y., Pan, Y., Yang, H., Yao, T. & Mei, T. Vp3d: Unleashing 2d visual prompt for text-to-3d generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4896\u20134905 (2024).","DOI":"10.1109\/CVPR52733.2024.00468"},{"key":"24916_CR14","doi-asserted-by":"publisher","first-page":"4296","DOI":"10.1609\/aaai.v38i5.28226","volume":"38","author":"C Mou","year":"2024","unstructured":"Mou, C. et al. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. In Proceedings of the AAAI conference on artificial intelligence 38, 4296\u20134304 (2024).","journal-title":"In Proceedings of the AAAI conference on artificial intelligence"},{"key":"24916_CR15","first-page":"8406","volume":"36","author":"Z Wang","year":"2023","unstructured":"Wang, Z. et al. Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. Advances in neural information processing systems 36, 8406\u20138441 (2023).","journal-title":"Advances in neural information processing systems"},{"key":"24916_CR16","doi-asserted-by":"crossref","unstructured":"Guo, C. et al. Generating diverse and natural 3d human motions from text. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 5152\u20135161 (2022).","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"24916_CR17","doi-asserted-by":"crossref","unstructured":"Liang, Y. et al. Luciddreamer: Towards high-fidelity text-to-3d generation via interval score matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 6517\u20136526 (2024).","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"24916_CR18","unstructured":"Li, W., Chen, R., Chen, X. & Tan, P. Sweetdreamer: Aligning geometric priors in 2d diffusion for consistent text-to-3d. arXiv preprint arXiv:2310.02596 (2023)."},{"key":"24916_CR19","unstructured":"Yi, T. et al. Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors. CoRR (2023)."},{"key":"24916_CR20","doi-asserted-by":"crossref","unstructured":"Richardson, E., Metzer, G., Alaluf, Y., Giryes, R. & Cohen-Or, D. Texture: Text-guided texturing of 3d shapes. In ACM SIGGRAPH 2023 conference proceedings, 1\u201311 (2023).","DOI":"10.1145\/3588432.3591503"},{"key":"24916_CR21","doi-asserted-by":"crossref","unstructured":"Mercier, A. et al. Hexagen3d: Stablediffusion is just one step away from fast and diverse text-to-3d generation. arXiv preprint arXiv:2401.07727 (2024).","DOI":"10.1109\/WACV61041.2025.00129"},{"key":"24916_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Qi, X. & Fu, C.-W. Towards implicit text-guided 3d shape generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 17896\u201317906 (2022).","DOI":"10.1109\/CVPR52688.2022.01737"},{"key":"24916_CR23","first-page":"10516","volume":"36","author":"N Kolotouros","year":"2023","unstructured":"Kolotouros, N. et al. Dreamhuman: Animatable 3d avatars from text. Advances in neural information processing systems 36, 10516\u201310529 (2023).","journal-title":"Advances in neural information processing systems"},{"key":"24916_CR24","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., Cao, A., Owens, A., Johnson, J. & Nie\u00dfner, M. Text2room: Extracting textured 3d meshes from 2d text-to-image models. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 7909\u20137920 (2023).","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"24916_CR25","first-page":"121859","volume":"37","author":"S Wu","year":"2024","unstructured":"Wu, S. et al. Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer. Advances in Neural Information Processing Systems 37, 121859\u2013121881 (2024).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"24916_CR26","doi-asserted-by":"publisher","first-page":"7320","DOI":"10.1609\/aaai.v39i7.32787","volume":"39","author":"Z Tang","year":"2025","unstructured":"Tang, Z. et al. Cycle3d: High-quality and consistent image-to-3d generation via generation-reconstruction cycle. In Proceedings of the AAAI Conference on Artificial Intelligence 39, 7320\u20137328 (2025).","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"24916_CR27","doi-asserted-by":"crossref","unstructured":"Xue, Y., Xie, X., Marin, R. & Pons-Moll, G. Gen-3diffusion: Realistic image-to-3d generation via 2d & 3d diffusion synergy. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025).","DOI":"10.1109\/TPAMI.2025.3577067"},{"key":"24916_CR28","doi-asserted-by":"crossref","unstructured":"Wen, H., Huang, Z., Wang, Y., Chen, X. & Sheng, L. Ouroboros3d: Image-to-3d generation via 3d-aware recursive diffusion. In Proceedings of the Computer Vision and Pattern Recognition Conference, 21631\u201321641 (2025).","DOI":"10.1109\/CVPR52734.2025.02015"},{"key":"24916_CR29","doi-asserted-by":"crossref","unstructured":"Liu, M. et al. One-2-3-45++: Fast single image to 3d objects with consistent multi-view generation and 3d diffusion. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 10072\u201310083 (2024).","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"24916_CR30","first-page":"22226","volume":"36","author":"M Liu","year":"2023","unstructured":"Liu, M. et al. One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization. Advances in Neural Information Processing Systems 36, 22226\u201322246 (2023).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"24916_CR31","doi-asserted-by":"crossref","unstructured":"Lee, H., Savva, M. & Chang, A.\u00a0X. Text-to-3d shape generation. In Computer Graphics Forum, vol.\u00a043, e15061 (Wiley Online Library, 2024).","DOI":"10.1111\/cgf.15061"},{"key":"24916_CR32","doi-asserted-by":"crossref","unstructured":"Cheng, T.-Y. et al. Learning continuous 3d words for text-to-image generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6753\u20136762 (2024).","DOI":"10.1109\/CVPR52733.2024.00645"},{"key":"24916_CR33","doi-asserted-by":"crossref","unstructured":"Tang, J. et al. Make-it-3d: High-fidelity 3d creation from a single image with diffusion prior. In Proceedings of the IEEE\/CVF international conference on computer vision, 22819\u201322829 (2023).","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"24916_CR34","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, B., Go, H., Kim, J.-Y. & Kim, C. Harmonyview: Harmonizing consistency and diversity in one-image-to-3d. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10574\u201310584 (2024).","DOI":"10.1109\/CVPR52733.2024.01006"},{"key":"24916_CR35","first-page":"67021","volume":"36","author":"E Ntavelis","year":"2023","unstructured":"Ntavelis, E. et al. Autodecoding latent 3d diffusion models. Advances in Neural Information Processing Systems 36, 67021\u201367047 (2023).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"24916_CR36","doi-asserted-by":"publisher","unstructured":"Sun, X. et al. Pix3d: Dataset and methods for single-image 3d shape modeling. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2974\u20132983, https:\/\/doi.org\/10.1109\/CVPR.2018.00314 (IEEE, 2018).","DOI":"10.1109\/CVPR.2018.00314"},{"key":"24916_CR37","doi-asserted-by":"publisher","unstructured":"Wu, T. et al. Omniobject3d: Large-vocabulary 3d object dataset for realistic perception, reconstruction and generation. arXiv preprint arXiv:2301.07525https:\/\/doi.org\/10.48550\/arXiv.2301.07525 (2023).","DOI":"10.48550\/arXiv.2301.07525"},{"key":"24916_CR38","unstructured":"Jun, H. & Nichol, A. Shap-e: Generating conditional 3d implicit functions. arXiv preprint arXiv:2305.02463 (2023)."},{"key":"24916_CR39","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0950-3293(01)00039-8","volume":"13","author":"AS Szczesniak","year":"2002","unstructured":"Szczesniak, A. S. Texture is a sensory property. Food quality and preference 13, 215\u2013225 (2002).","journal-title":"Food quality and preference"},{"key":"24916_CR40","doi-asserted-by":"crossref","unstructured":"Chen, D.\u00a0Z., Siddiqui, Y., Lee, H.-Y., Tulyakov, S. & Nie\u00dfner, M. Text2tex: Text-driven texture synthesis via diffusion models. In Proceedings of the IEEE\/CVF international conference on computer vision, 18558\u201318568 (2023).","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"24916_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, H., Pan, Z., Zhang, C., Zhu, L. & Gao, X. Texpainter: Generative mesh texturing with multi-view consistency. In Acm siggraph 2024 conference papers, 1\u201311 (2024).","DOI":"10.1145\/3641519.3657494"},{"key":"24916_CR42","doi-asserted-by":"crossref","unstructured":"Liu, F., Wu, D., Wei, Y., Rao, Y. & Duan, Y. Sherpa3d: Boosting high-fidelity text-to-3d generation via coarse 3d prior. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 20763\u201320774 (2024).","DOI":"10.1109\/CVPR52733.2024.01962"},{"key":"24916_CR43","doi-asserted-by":"crossref","unstructured":"Wang, J. et al. Mvtexgen: Synthesising 3d textures using multi-view diffusion. In 2024 IEEE International Conference on Multimedia and Expo (ICME), 1\u20136 (IEEE, 2024).","DOI":"10.1109\/ICME57554.2024.10687386"},{"key":"24916_CR44","doi-asserted-by":"crossref","unstructured":"Zeng, X. et al. Paint3d: Paint anything 3d with lighting-less texture diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 4252\u20134262 (2024).","DOI":"10.1109\/CVPR52733.2024.00407"},{"key":"24916_CR45","unstructured":"Yang, X. et al. Hunyuan3d 1.0: A unified framework for text-to-3d and image-to-3d generation. arXiv preprint arXiv:2411.02293 (2024)."},{"key":"24916_CR46","unstructured":"Xu, J. et al. Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models (2024). arXiv:2404.07191."},{"key":"24916_CR47","unstructured":"Hong, Y. et al. Lrm: Large reconstruction model for single image to 3d (2024). arXiv:2311.04400."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24916-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24916-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24916-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T11:04:46Z","timestamp":1763636686000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24916-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["24916"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-24916-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,20]]},"assertion":[{"value":"21 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"41084"}}