{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:07:22Z","timestamp":1772644042590,"version":"3.50.1"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["No. LY23F020005"],"award-info":[{"award-number":["No. LY23F020005"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62572164"],"award-info":[{"award-number":["No. 62572164"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s00371-025-04322-9","type":"journal-article","created":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T15:27:44Z","timestamp":1767886064000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SwiftCraft3D: semantic-enhanced multi-view prompting for efficient and high-fidelity text-to-3D generation"],"prefix":"10.1007","volume":"42","author":[{"given":"Zeyi","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,8]]},"reference":[{"issue":"7","key":"4322_CR1","doi-asserted-by":"publisher","first-page":"5229","DOI":"10.1109\/TCSVT.2023.3341805","volume":"34","author":"P Li","year":"2024","unstructured":"Li, P., Gao, C., Liu, F., Meng, D., Yan, Y.: Thisnet: tooth instance segmentation on 3d dental models via highlighting tooth regions. IEEE Trans. Circuits Syst. Video Technol. 34(7), 5229\u20135241 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"4322_CR2","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1109\/TCSVT.2023.3289885","volume":"34","author":"C Qi","year":"2024","unstructured":"Qi, C., Yin, J., Xu, J., Ding, P.: Instance-incremental scene graph generation from real-world point clouds via normalizing flows. IEEE Trans. Circuits Syst. Video Technol. 34(2), 1057\u20131069 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"4","key":"4322_CR3","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.vrih.2023.06.010","volume":"6","author":"C Pan","year":"2024","unstructured":"Pan, C., Yang, G., Mu, T., Lai, Y.: Generating animatable 3d cartoon faces from single portraits. Virtual Real. Intell. Hardw. 6(4), 292\u2013307 (2024). https:\/\/doi.org\/10.1016\/j.vrih.2023.06.010","journal-title":"Virtual Real. Intell. Hardw."},{"issue":"1","key":"4322_CR4","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TNNLS.2022.3175775","volume":"35","author":"A Karambakhsh","year":"2024","unstructured":"Karambakhsh, A., Sheng, B., Li, P., Li, H., Kim, J., Jung, Y., Chen, C.L.P.: Sparsevoxnet: 3-d object recognition with sparsely aggregation of 3-d dense blocks. IEEE Trans. Neural Netw. Learn. Syst. 35(1), 532\u2013546 (2024). https:\/\/doi.org\/10.1109\/TNNLS.2022.3175775","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"6","key":"4322_CR5","doi-asserted-by":"publisher","first-page":"4229","DOI":"10.1109\/TCSVT.2023.3328371","volume":"34","author":"B Huang","year":"2024","unstructured":"Huang, B., Ju, J., Shu, Y., Wang, Y.: Simultaneously recovering multi-person meshes and multi-view cameras with human semantics. IEEE Trans. Circuits Syst. Video Technol. 34(6), 4229\u20134242 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4322_CR6","doi-asserted-by":"publisher","unstructured":"Yao, J., Chen, J., Niu, L., Sheng, B.: Scene-aware human pose generation using transformer. In Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023, A.\u00a0El-Saddik, T.\u00a0Mei, R.\u00a0Cucchiara, M.\u00a0Bertini, D.\u00a0P.\u00a0T. Vallejo, P.\u00a0K. Atrey, and M.\u00a0S. Hossain, Eds. ACM, pp. 2847\u20132855. (2023) [Online]. Available: https:\/\/doi.org\/10.1145\/3581783.3612439","DOI":"10.1145\/3581783.3612439"},{"issue":"1","key":"4322_CR7","doi-asserted-by":"publisher","first-page":"e2215","DOI":"10.1002\/cav.2215","volume":"35","author":"X Li","year":"2024","unstructured":"Li, X., Huang, Y., Jiang, Z., Liu, Y., Hou, Y.: Rendering and presentation of 3d digital ink landscape painting. Comput. Animat. Virtual Worlds 35(1), e2215 (2024). https:\/\/doi.org\/10.1002\/cav.2215","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"4322_CR8","doi-asserted-by":"publisher","unstructured":"Lin, C., Gao, J., Tang, L., Takikawa, T., Zeng, X., Huang, X., Kreis, K., Fidler, S., Liu, M., Lin, T.: Magic3d: High-resolution text-to-3d content creation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. IEEE, pp. 300\u2013309. (2023) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52729.2023.00037","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"4322_CR9","doi-asserted-by":"publisher","unstructured":"Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3d: disentangling geometry and appearance for high-quality text-to-3d content creation. In: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. IEEE, pp. 22\u00a0189\u201322\u00a0199. (2023) [Online]. Available: https:\/\/doi.org\/10.1109\/ICCV51070.2023.02033","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"4322_CR10","doi-asserted-by":"publisher","unstructured":"Liu, F., Wu, D., Wei, Y., Rao, Y., Duan, Y.: Sherpa3d: boosting high-fidelity text-to-3d generation via coarse 3d prior. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 20\u00a0763\u201320\u00a0774. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.01962","DOI":"10.1109\/CVPR52733.2024.01962"},{"key":"4322_CR11","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, (2023). [Online]. Available: https:\/\/openreview.net\/forum?id=FjNys5c7VyY"},{"key":"4322_CR12","doi-asserted-by":"publisher","unstructured":"Metzer, G., Richardson, E., Patashnik, O., Giryes, R., Cohen-Or, D.: Latent-nerf for shape-guided generation of 3d shapes and textures. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. IEEE, pp. 12\u00a0663\u201312\u00a0673. (2023) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52729.2023.01218","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"4322_CR13","doi-asserted-by":"publisher","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score jacobian chaining: lifting pretrained 2d diffusion models for 3d generation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. IEEE, pp. 12\u00a0619\u201312\u00a0629. (2023) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52729.2023.01214","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"4322_CR14","doi-asserted-by":"publisher","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: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. IEEE, pp. 7875\u20137886. (2023) [Online]. Available: https:\/\/doi.org\/10.1109\/ICCV51070.2023.00727","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"4322_CR15","doi-asserted-by":"publisher","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, pp. 857\u2013866. (2022) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52688.2022.00094","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"4322_CR16","doi-asserted-by":"publisher","unstructured":"Khalid, N.M., Xie, T., Belilovsky, E., Popa, T.: Clip-mesh: generating textured meshes from text using pretrained image-text models. In: SIGGRAPH Asia 2022 Conference Papers, SA 2022, Daegu, Republic of Korea, December 6-9, 2022, S.\u00a0K. Jung, J.\u00a0Lee, and A.\u00a0W. Bargteil, Eds. ACM, pp. 25:1\u201325:8. (2022) [Online]. Available: https:\/\/doi.org\/10.1145\/3550469.3555392","DOI":"10.1145\/3550469.3555392"},{"key":"4322_CR17","unstructured":"Wang, Z., Lu, C., Wang, Y., Bao, F., Li, C., Su, H., Zhu, J.: Prolificdreamer: high-fidelity and diverse text-to-3d generation with variational score distillation. In: Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, A.\u00a0Oh, T.\u00a0Naumann, A.\u00a0Globerson, K.\u00a0Saenko, M.\u00a0Hardt, and S.\u00a0Levine, Eds., (2023). [Online]. Available: http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/1a87980b9853e84dfb295855b425c262-Abstract-Conference.html"},{"key":"4322_CR18","doi-asserted-by":"publisher","unstructured":"Liang, Y., Yang, X., Lin, J., Li, H., Xu, X., Chen, Y.: Luciddreamer: towards high-fidelity text-to-3d generation via interval score matching. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 6517\u20136526. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.00623","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"4322_CR19","doi-asserted-by":"publisher","unstructured":"Wu, Z., Zhou, P., Yi, X., Yuan, X., Zhang, H.: Consistent3d: towards consistent high-fidelity text-to-3d generation with deterministic sampling prior. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 9892\u20139902. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.00944","DOI":"10.1109\/CVPR52733.2024.00944"},{"key":"4322_CR20","doi-asserted-by":"publisher","unstructured":"Chen, Z., Wang, F., Wang, Y., Liu, H.: Text-to-3d using gaussian splatting. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 21\u00a0401\u201321\u00a0412. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.02022","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"4322_CR21","unstructured":"Jun, H., Nichol, A.: Shap-e: generating conditional 3d implicit functions. arXiv preprint arXiv:2305.02463, (2023)"},{"issue":"7","key":"4322_CR22","doi-asserted-by":"publisher","first-page":"4701","DOI":"10.1007\/s00371-024-03463-7","volume":"40","author":"H Xu","year":"2024","unstructured":"Xu, H., Wu, Y., Tang, X., Zhang, J., Zhang, Y., Zhang, Z., Li, C., Jin, X.: Fusiondeformer: text-guided mesh deformation using diffusion models\u2019\u2019. Visual Comput. 40(7), 4701\u20134712 (2024). https:\/\/doi.org\/10.1007\/s00371-024-03463-7","journal-title":"Visual Comput."},{"key":"4322_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.\u00a0Balcan, and H.\u00a0Lin, Eds., (2020). [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html"},{"key":"4322_CR24","doi-asserted-by":"publisher","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, pp. 10\u00a0674\u201310\u00a0685. (2022) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01042","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"4322_CR25","unstructured":"Saharia, C., Chan, W., Saxena, S, Li, L., Whang, J., Denton, E.L., Ghasemipour, S.K.S., Lopes, R.G., Ayan, B.K., Salimans, T., Ho, J., Fleet, D.J., Norouzi, M.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh, Eds., (2022). [Online]. Available: http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/ec795aeadae0b7d230fa35cbaf04c041-Abstract-Conference.html"},{"key":"4322_CR26","unstructured":"Dhariwal, P., Nichol, A.Q.: Diffusion models beat gans on image synthesis. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0N. Dauphin, P.\u00a0Liang, and J.\u00a0W. Vaughan, Eds., pp. 8780\u20138794. (2021) [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/49ad23d1ec9fa4bd8d77d02681df5cfa-Abstract.html"},{"key":"4322_CR27","unstructured":"Esser, P., Rombach, R., Blattmann, A., Ommer, B.: Imagebart: bidirectional context with multinomial diffusion for autoregressive image synthesis. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0N. Dauphin, P.\u00a0Liang, and J.\u00a0W. Vaughan, Eds., pp. 3518\u20133532. (2021) [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/1cdf14d1e3699d61d237cf76ce1c2dca-Abstract.html"},{"key":"4322_CR28","unstructured":"Gupta, A., Xiong, W., Nie, Y., Jones, I., O\u011fuz, B.: 3dgen: triplane latent diffusion for textured mesh generation. arXiv preprint arXiv:2303.05371, (2023)"},{"key":"4322_CR29","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-e: a system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751, (2022)"},{"key":"4322_CR30","unstructured":"Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et\u00a0al.: Shapenet: an information-rich 3d model repository. arXiv preprint arXiv:1512.03012, (2015)"},{"key":"4322_CR31","doi-asserted-by":"publisher","unstructured":"Deitke, M., Schwenk, D., Salvador, J., Weihs, L., Michel, O., VanderBilt, E., Schmidt, L., Ehsani, K., Kembhavi, A., Farhadi, A.: Objaverse: a universe of annotated 3d objects. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. IEEE, pp. 13\u00a0142\u201313\u00a0153. (2023) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52729.2023.01263","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"4322_CR32","unstructured":"Deitke, M., Liu, R., Wallingford, M., Ngo, H., Michel, O., Kusupati, A., Fan, A., Laforte, C., Voleti, V., Gadre, S.Y., VanderBilt, E., Kembhavi, A., Vondrick, C., Gkioxari, G., Ehsani, K., Schmidt, L., Farhadi, A.: Objaverse-xl: a universe of 10m+ 3d objects. In: Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, A.\u00a0Oh, T.\u00a0Naumann, A.\u00a0Globerson, K.\u00a0Saenko, M.\u00a0Hardt, and S.\u00a0Levine, Eds., (2023). [Online]. Available: http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/70364304877b5e767de4e9a2a511be0c-Abstract-Datasets_and_Benchmarks.html"},{"key":"4322_CR33","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., Schramowski, P., Kundurthy, S., Crowson, K., Schmidt, L., Kaczmarczyk, R., Jitsev, J.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh, Eds., (2022). [Online]. Available: http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/a1859debfb3b59d094f3504d5ebb6c25-Abstract-Datasets_and_Benchmarks.html"},{"issue":"1","key":"4322_CR34","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2022","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2022). https:\/\/doi.org\/10.1145\/3503250","journal-title":"Commun. ACM"},{"key":"4322_CR35","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774, (2023)"},{"key":"4322_CR36","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., Rombach, R.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net, (2024). [Online]. Available: https:\/\/openreview.net\/forum?id=di52zR8xgf"},{"key":"4322_CR37","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: Lora: low-rank adaptation of large language models. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net, (2022). [Online]. Available: https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"4322_CR38","unstructured":"Shi, R., Chen, H., Zhang, Z., Liu, M., Xu, C., Wei, X., Chen, L., Zeng, C., Su, H.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110, (2023)"},{"key":"4322_CR39","unstructured":"Hong, Y., Zhang, K., Gu, J., Bi, S., Zhou, Y., Liu, D., Liu, F., Sunkavalli, K., Bui, T., Tan, H.: Lrm: large reconstruction model for single image to 3d. arXiv preprint arXiv:2311.04400, (2023)"},{"issue":"4","key":"4322_CR40","doi-asserted-by":"publisher","first-page":"37:1","DOI":"10.1145\/3592430","volume":"42","author":"T Shen","year":"2023","unstructured":"Shen, T., Munkberg, J., Hasselgren, J., Yin, K., Wang, Z., Chen, W., Gojcic, Z., Fidler, S., Sharp, N., Gao, J.: Flexible isosurface extraction for gradient-based mesh optimization. ACM Trans. Graph. 42(4), 37:1-37:16 (2023). https:\/\/doi.org\/10.1145\/3592430","journal-title":"ACM Trans. Graph."},{"issue":"3","key":"4322_CR41","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1109\/TCSVT.2023.3296889","volume":"34","author":"T Yu","year":"2024","unstructured":"Yu, T., Lin, X., Wang, S., Sheng, W., Huang, Q., Yu, J.: A comprehensive survey of 3d dense captioning: localizing and describing objects in 3d scenes. IEEE Trans. Circuits Syst. Video Technol. 34(3), 1322\u20131338 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"4322_CR42","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1007\/s00371-024-03370-x","volume":"41","author":"T Yu","year":"2025","unstructured":"Yu, T., Meng, W., Wu, Z., Guo, J., Zhang, X.: Diff-pcg: diffusion point cloud generation conditioned on continuous normalizing flow. Visual Comput. 41(2), 853\u2013867 (2025). https:\/\/doi.org\/10.1007\/s00371-024-03370-x","journal-title":"Visual Comput."},{"key":"4322_CR43","doi-asserted-by":"publisher","unstructured":"Chen, Y., Pan, Y., Yang, H., Yao, T., Mei, T.: VP3D: unleashing 2d visual prompt for text-to-3d generation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 4896\u20134905. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.00468","DOI":"10.1109\/CVPR52733.2024.00468"},{"key":"4322_CR44","doi-asserted-by":"publisher","unstructured":"Qiu, L., Chen, G., Gu, X., Zuo, Q., Xu, M., Wu, Y., Yuan, W., Dong, Z., Bo, L., Han, X.: Richdreamer: a generalizable normal-depth diffusion model for detail richness in text-to-3d. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 9914\u20139925. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.00946","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"4322_CR45","doi-asserted-by":"publisher","unstructured":"Liu, R., Wu, R., Hoorick, B.V., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3d object. In: IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. IEEE, pp. 9264\u20139275. (2023) [Online]. Available: https:\/\/doi.org\/10.1109\/ICCV51070.2023.00853","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"4322_CR46","unstructured":"Shi, Y., Wang, P., Ye, J., Mai,L., Li, K., Yang, X.: Mvdream: multi-view diffusion for 3d generation. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net, (2024). [Online]. Available: https:\/\/openreview.net\/forum?id=FUgrjq2pbB"},{"key":"4322_CR47","unstructured":"Liu, Y., Lin, C., Zeng, Z., Long, X., Liu, L., Komura, T., Wang, W.: Syncdreamer: generating multiview-consistent images from a single-view image. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net, (2024). [Online]. Available: https:\/\/openreview.net\/forum?id=MN3yH2ovHb"},{"key":"4322_CR48","unstructured":"Wang, P., Shi, Y.: Imagedream: image-prompt multi-view diffusion for 3d generation. arXiv preprint arXiv:2312.02201, (2023)"},{"key":"4322_CR49","doi-asserted-by":"publisher","unstructured":"Kant, Y., Siarohin, A., Wu, Z., Vasilkovsky, M., Qian, G., Ren, J., G\u00fcler, A., Ghanem, B., Tulyakov, S., Gilitschenski, I.: SPAD: spatially aware multi-view diffusers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 10\u00a0026\u201310\u00a0038. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.00956","DOI":"10.1109\/CVPR52733.2024.00956"},{"key":"4322_CR50","doi-asserted-by":"publisher","unstructured":"Voleti V., Yao C., Boss M., Letts A., Pankratz D., Tochilkin D., Laforte C., Rombach R., Jampani, V.: SV3D: novel multi-view synthesis and 3d generation from a single image using latent video diffusion. In: Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part I, ser. Lecture Notes in Computer Science, A.\u00a0Leonardis, E.\u00a0Ricci, S.\u00a0Roth, O.\u00a0Russakovsky, T.\u00a0Sattler, and G.\u00a0Varol, Eds., vol. 15059. Springer, pp. 439\u2013457. (2024) [Online]. Available: https:\/\/doi.org\/10.1007\/978-3-031-73232-4_25","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"4322_CR51","doi-asserted-by":"publisher","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III, ser. Lecture Notes in Computer Science, B.\u00a0Leibe, J.\u00a0Matas, N.\u00a0Sebe, and M.\u00a0Welling, Eds., vol. 9907. Springer, pp. 501\u2013518. (2016) [Online]. Available: https:\/\/doi.org\/10.1007\/978-3-319-46487-9_31","DOI":"10.1007\/978-3-319-46487-9_31"},{"issue":"10","key":"4322_CR52","doi-asserted-by":"publisher","first-page":"5153","DOI":"10.1007\/s00371-022-02651-7","volume":"39","author":"R Chen","year":"2023","unstructured":"Chen, R., Yin, X., Yang, Y., Tong, C.: Multi-view pixel2mesh++: 3d reconstruction via pixel2mesh with more images. Visual Comput. 39(10), 5153\u20135166 (2023). https:\/\/doi.org\/10.1007\/s00371-022-02651-7","journal-title":"Visual Comput."},{"issue":"1","key":"4322_CR53","doi-asserted-by":"publisher","first-page":"e221","DOI":"10.1002\/cav.2201","volume":"35","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Yao, X., Zhang, J., Zhu, M., You, L., Yang, X., Zhang, J.J., Zhao, H., Zeng, D.: Tmsdnet: transformer with multi-scale dense network for single and multi-view 3d reconstruction. Comput. Animat. Virtual Worlds 35(1), e221 (2024). https:\/\/doi.org\/10.1002\/cav.2201","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"4322_CR54","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-025-03899-5","author":"SM Hosseini","year":"2025","unstructured":"Hosseini, S.M., Nasiri, S.-M., Hosseini, R., Moradi, H.: Single-view 3d reconstruction of surface of revolution. Visual Comput. (2025). https:\/\/doi.org\/10.1007\/s00371-025-03899-5","journal-title":"Visual Comput."},{"issue":"7","key":"4322_CR55","doi-asserted-by":"publisher","first-page":"4851","DOI":"10.1007\/s00371-024-03694-8","volume":"41","author":"J Wang","year":"2025","unstructured":"Wang, J., Li, H., Chen, Y.: Seg-invrender: fusing semantic segmentation based on nerf for inverse rendering considering shadows. Visual Comput. 41(7), 4851\u20134864 (2025). https:\/\/doi.org\/10.1007\/s00371-024-03694-8","journal-title":"Visual Comput."},{"key":"4322_CR56","doi-asserted-by":"publisher","unstructured":"Dai, A., Chang, A.\u00a0X., Savva, M., Halber, M., Funkhouser, T.A., Nie\u00dfner, M.: Scannet: richly-annotated 3d reconstructions of indoor scenes. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017. IEEE Computer Society, pp. 2432\u20132443. (2017) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR.2017.261","DOI":"10.1109\/CVPR.2017.261"},{"key":"4322_CR57","unstructured":"Li, J., Tan, H., Zhang, K., Xu, Z., Luan, F., Xu, Y., Hong, Y., Sunkavalli, K., Shakhnarovich, G., Bi, S.: Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net, (2024). [Online]. Available: https:\/\/openreview.net\/forum?id=2lDQLiH1W4"},{"key":"4322_CR58","unstructured":"Xu, J., Cheng, W., Gao, Y., Wang, X., Gao, S., Shan, Y.: Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models. arXiv preprint arXiv:2404.07191, (2024)"},{"key":"4322_CR59","doi-asserted-by":"publisher","unstructured":"Zou, Z., Yu, Z., Guo, Y., Li, Y., Liang, D., Cao, Y., Zhang, S.: Triplane meets gaussian splatting: fast and generalizable single-view 3d reconstruction with transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 10\u00a0324\u201310\u00a0335. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.00983","DOI":"10.1109\/CVPR52733.2024.00983"},{"key":"4322_CR60","doi-asserted-by":"publisher","unstructured":"Wang, Z., Wang, Y., Chen, Y., Xiang, C., Chen, S., Yu, D., Li, C., Su, H., Zhu, J.: CRM: single image to 3d textured mesh with convolutional reconstruction model. In: Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part XXXI, ser. Lecture Notes in Computer Science, A.\u00a0Leonardis, E.\u00a0Ricci, S.\u00a0Roth, O.\u00a0Russakovsky, T.\u00a0Sattler, and G.\u00a0Varol, Eds., vol. 15089. Springer, pp. 57\u201374. (2024) [Online]. Available: https:\/\/doi.org\/10.1007\/978-3-031-72751-1_4","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"4322_CR61","doi-asserted-by":"publisher","unstructured":"Liu, M., Shi, R., Chen, L., Zhang, Z., Xu, C., Wei, X., Chen, H., Zeng, C., Gu, J., Su, H.: One-2-3-45++: fast single image to 3d objects with consistent multi-view generation and 3d diffusion. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 10\u00a0072\u201310\u00a0083. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.00960","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"4322_CR62","unstructured":"He, Y., Bai, Y., Lin, M., Zhao, W., Hu, Y., Sheng, J., Yi, R., Li, J., Liu, Y.-J.: T$$^3$$bench: benchmarking current progress in text-to-3d generation. arXiv preprint arXiv:2310.02977, (2023)"},{"key":"4322_CR63","doi-asserted-by":"publisher","unstructured":"Wu, T., Yang, G., Li, Z., Zhang, K., Liu, Z., Guibas, L.J., Lin, D., Wetzstein, G.: Gpt-4v(ision) is a human-aligned evaluator for text-to-3d generation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. IEEE, pp. 22\u00a0227\u201322\u00a0238. (2024) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52733.2024.02098","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"4322_CR64","unstructured":"Luo, T., Rockwell, C., Lee, H., Johnson, J.: Scalable 3d captioning with pretrained models. In: Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, A.\u00a0Oh, T.\u00a0Naumann, A.\u00a0Globerson, K.\u00a0Saenko, M.\u00a0Hardt, and S.\u00a0Levine, Eds., (2023). [Online]. Available: http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/ee4814f9bce0cae7991d3341bb081b55-Abstract-Datasets_and_Benchmarks.html"},{"key":"4322_CR65","doi-asserted-by":"publisher","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. IEEE, pp. 9630\u20139640. (2021) [Online]. Available: https:\/\/doi.org\/10.1109\/ICCV48922.2021.00951","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"4322_CR66","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), J.\u00a0Burstein, C.\u00a0Doran, and T.\u00a0Solorio, Eds. Association for Computational Linguistics, pp. 4171\u20134186. (2019) [Online]. Available: https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"4322_CR67","doi-asserted-by":"publisher","unstructured":"Chan, E.R., Lin, C.Z., Chan, M.A., Nagano, K., Pan, B., Mello, S.D., Gallo, O., Guibas, L.J., Tremblay, J., Khamis, S., Karras, T., Wetzstein, G.: Efficient geometry-aware 3d generative adversarial networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, pp. 16\u00a0102\u201316\u00a0112. (2022) [Online]. Available: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01565","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"4322_CR68","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: Deepsdf: learning continuous signed distance functions for shape representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (June 2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"4322_CR69","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3d shape synthesis. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0N. Dauphin, P.\u00a0Liang, and J.\u00a0W. Vaughan, Eds., pp. 6087\u20136101. (2021) [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/30a237d18c50f563cba4531f1db44acf-Abstract.html"},{"key":"4322_CR70","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Y.\u00a0Bengio and Y.\u00a0LeCun, Eds., (2015). [Online]. Available: http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"4322_CR71","unstructured":"Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X.: Mvdream: multi-view diffusion for 3d generation. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net, (2024). [Online]. Available: https:\/\/openreview.net\/forum?id=FUgrjq2pbB"},{"key":"4322_CR72","unstructured":"Liu, Y., Lin, C., Zeng, Z., Long, X., Liu, L., Komura, T., Wang, W.: Syncdreamer: generating multiview-consistent images from a single-view image. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net, (2024). [Online]. Available: https:\/\/openreview.net\/forum?id=MN3yH2ovHb"},{"key":"4322_CR73","doi-asserted-by":"publisher","unstructured":"Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3d surface construction algorithm. In: Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1987, Anaheim, California, USA, July 27-31, 1987, M.\u00a0C. Stone, Ed. ACM, pp. 163\u2013169. (1987) [Online]. Available: https:\/\/doi.org\/10.1145\/37401.37422","DOI":"10.1145\/37401.37422"},{"key":"4322_CR74","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3d shape synthesis. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0N. Dauphin, P.\u00a0Liang, and J.\u00a0W. Vaughan, Eds., pp. 6087\u20136101. (2021) [Online]. Available: https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/30a237d18c50f563cba4531f1db44acf-Abstract.html"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04322-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04322-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04322-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:04:18Z","timestamp":1772629458000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04322-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":74,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4322"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04322-9","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"6 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2026","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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"118"}}