{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:34:50Z","timestamp":1757619290442,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":48,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819698653"},{"type":"electronic","value":"9789819698660"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-9866-0_31","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T09:24:24Z","timestamp":1753262664000},"page":"358-369","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["V2Tex: High-Fidelity Texture Generation for 3D Meshes from Text Using Video Diffusion Models"],"prefix":"10.1007","author":[{"given":"Zhenqiang","family":"Li","sequence":"first","affiliation":[]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yangjie","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Runfeng","family":"Lv","sequence":"additional","affiliation":[]},{"given":"Lijie","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Ashikhmin, M.: Synthesizing natural textures. In: Proceedings of the 2001 Symposium on Interactive 3D Graphics, pp. 217\u2013226 (2001)","DOI":"10.1145\/364338.364405"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Cao, T., Kreis, K., Fidler, S., Sharp, N., Yin, K.: Texfusion: synthesizing 3d textures with text-guided image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4169\u20134181 (2023)","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., 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, pp. 18558\u201318568 (2023)","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Siddiqui, Y., Lee, H.Y., Tulyakov, S., Nie\u00dfner, M.: Text2tex: Text- driven texture synthesis via diffusion models. arXiv preprint arXiv:2303.11396 (2023)","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"31_CR5","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, pp. 22246\u201322256 (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: gdna: towards generative detailed neural avatars. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20427\u201320437 (2022)","DOI":"10.1109\/CVPR52688.2022.01978"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, Y., Wang, F., Wang, Z., Liu, H.: V3d: video diffusion models are effective 3d generators. arXiv preprint arXiv:2403.06738 (2024)","DOI":"10.1109\/TPAMI.2025.3581312"},{"key":"31_CR8","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34, 8780\u20138794 (2021)","journal-title":"Advances in neural information processing systems"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Dong, Z., Chen, X., Yang, J., Black, M.J., Hilliges, O., Geiger, A.: Ag3d: learning to generate 3d avatars from 2d image collections. arXiv preprint arXiv:2305.02312 (2023)","DOI":"10.1109\/ICCV51070.2023.01370"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1033\u20131038. IEEE (1999)","DOI":"10.1109\/ICCV.1999.790383"},{"key":"31_CR11","unstructured":"Hong, Y., et al.: Lrm: large reconstruction model for single image to 3d. arXiv preprint arXiv:2311.04400 (2023)"},{"issue":"4","key":"31_CR12","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139\u20131 (2023)","journal-title":"ACM Trans. Graph."},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Kopf, J., Fu, C.W., Cohen-Or, D., Deussen, O., Lischinski, D., Wong, T.T.: Solid texture synthesis from 2d exemplars. In: ACM SIGGRAPH 2007 Papers, pp. 2\u2013es (2007)","DOI":"10.1145\/1275808.1276380"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Kwatra, V., Essa, I., Bobick, A., Kwatra, N.: Texture optimization for example- based synthesis. In: ACM SIGGRAPH 2005 Papers, pp. 795\u2013802 (2005)","DOI":"10.1145\/1186822.1073263"},{"key":"31_CR15","unstructured":"Le, C., Hetang, C., Cao, A., He, Y.: Euclidreamer: fast and high-quality texturing for 3d models with stable diffusion depth. arXiv preprint arXiv:2311.15573 (2023)"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., Jie, L., Cao, Y., Wang, J., Lv, R.: Imagebind3d: Image as binding step for controllable 3d generation. In: ACM Multimedia 2024","DOI":"10.1145\/3664647.3680845"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Liang, J., Fan, Y., Zhang, K., Timofte, R., Van Gool, L., Ranjan, R.: Movideo: motion-aware video generation with diffusion model. In: European Conference on Computer Vision, pp. 56\u201374. Springer (2024)","DOI":"10.1007\/978-3-031-72784-9_4"},{"key":"31_CR18","doi-asserted-by":"crossref","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6517\u20136526 (2024)","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero- 1-to-3: zero-shot one image to 3d object. In: Proceedings of the IEEE\/CVF Inter- national Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"31_CR20","unstructured":"Liu, Y., et al.: Syncdreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xie, M., Liu, H., Wong, T.T.: Text-guided texturing by synchronized multi-view diffusion. arXiv preprint arXiv:2311.12891 (2023)","DOI":"10.1145\/3680528.3687621"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Lu, J., et al.: Context-aware textures. ACM Trans. Graph. (TOG) 26(1), 3\u2013es (2007)","DOI":"10.1145\/1189762.1189765"},{"key":"31_CR23","unstructured":"Mertens, T., Kautz, J., Chen, J., Bekaert, P., Durand, F.: Texture transfer using geometry correlation. Rendering Techniques 273(10.2312), 273\u2013284 (2006)"},{"issue":"1","key":"31_CR24","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","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 (2021)","journal-title":"Commun. ACM"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Mohammad Khalid, N., Xie, T., Belilovsky, E., Popa, T.: Clip-mesh: generating textured meshes from text using pretrained image-text models. In: SIGGRAPH Asia 2022 Conference Papers, pp. 1\u20138 (2022)","DOI":"10.1145\/3550469.3555392"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Wu, Y., Zhang, J., Qi, Z., Shan, Y.: 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. vol. 38, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"31_CR27","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. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"31_CR28","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"31_CR29","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, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591503"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Richardson, E., Metzer, G., Alaluf, Y., Giryes, R., Cohen-Or, D.: Texture: text- guided texturing of 3d shapes. arXiv preprint arXiv:2302.01721 (2023)","DOI":"10.1145\/3588432.3591503"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dream- booth: Fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Sanghi, A., et al.: Clip-forge: towards zero-shot text-to-shape generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18603\u201318613 (2022)","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Schops, T., et al.: A multi-view stereo benchmark with high-resolution images and multi-camera videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3260\u20133269 (2017)","DOI":"10.1109\/CVPR.2017.272"},{"key":"31_CR35","unstructured":"Seo, J., et al.: Let 2d diffusion model know 3d-consistency for robust text-to-3d generation. arXiv preprint arXiv:2303.07937 (2023)"},{"key":"31_CR36","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512 (2023)"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: exploring photo collections in 3d. In: ACM siggraph 2006 Papers, pp. 835\u2013846 (2006)","DOI":"10.1145\/1141911.1141964"},{"key":"31_CR38","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"31_CR39","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Voleti, V., et al.: Sv3d: novel multi-view synthesis and 3d generation from a single image using latent video diffusion. In: European Conference on Computer Vision, pp. 439\u2013457. Springer (2024)","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"31_CR41","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":"31_CR42","doi-asserted-by":"crossref","unstructured":"Wong, T.T., Ng, W.Y., Heng, P.A.: A geometry dependent texture generation framework for simulating surface imperfections. In: Rendering Techniques\u2019 97: Proceedings of the Eurographics Workshop in St. Etienne, France, June 16\u201318, 1997, pp. 139\u2013150. Springer (1997)","DOI":"10.1007\/978-3-7091-6858-5_13"},{"key":"31_CR43","unstructured":"Wu, K., et al.: Unique3d: high-quality and efficient 3d mesh generation from a single image. In: The Thirty- Eighth Annual Conference on Neural Information Processing Systems (2024)"},{"key":"31_CR44","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: GRM: large Gaussian reconstruction model for efficient 3d reconstruction and generation. In: European Conference on Computer Vision, pp. 1\u201320. Springer (2024)","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"31_CR45","doi-asserted-by":"crossref","unstructured":"Yang, H., Chen, Y., Pan, Y., Yao, T., Chen, Z., Mei, T.: 3dstyle-diffusion: pursuing fine-grained text-driven 3d stylization with 2d diffusion models. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 6860\u20136868 (2023)","DOI":"10.1145\/3581783.3612363"},{"key":"31_CR46","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: Hi3d: pursuing high-resolution image-to-3d generation with video diffusion models. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 6870\u20136879 (2024)","DOI":"10.1145\/3664647.3681634"},{"key":"31_CR47","doi-asserted-by":"crossref","unstructured":"Yeh, Y.Y., et al.: Texturedreamer: image-guided texture synthesis through geometry-aware diffusion. arXiv preprint arXiv:2401.09416 (2024)","DOI":"10.1109\/CVPR52733.2024.00412"},{"key":"31_CR48","doi-asserted-by":"crossref","unstructured":"Youwang, K., Oh, T.H., Pons-Moll, G.: Paint-it: text-to-texture synthesis via deep convolutional texture map optimization and physically-based rendering. arXiv preprint arXiv:2312.11360 (2023)","DOI":"10.1109\/CVPR52733.2024.00416"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9866-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T19:51:05Z","timestamp":1757274665000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9866-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698653","9789819698660"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9866-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}