{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:39:39Z","timestamp":1743079179878,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785070"},{"type":"electronic","value":"9789819785087"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8508-7_12","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:12:09Z","timestamp":1730527929000},"page":"166-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MTFusion: Reconstructing Any 3D Object from Single Image Using Multi-word Textual Inversion"],"prefix":"10.1007","author":[{"given":"Yu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruowei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixiang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qijun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"12_CR1","unstructured":"Agarwal, A., Karanam, S., Shukla, T., Srinivasan, B.V.: An image is worth multiple words: multi-attribute inversion for constrained text-to-image synthesis (2023). arXiv:2311.11919"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., Srinivasan, P.P.: Mip-nerf: a multiscale representation for anti-aliasing neural radiance fields. In: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"12_CR3","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: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Fei, Z., Fan, M., Huang, J.: Gradient-free textual inversion. In: ACMMM (2023)","DOI":"10.1145\/3581783.3612599"},{"key":"12_CR5","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: ICLR (2023)"},{"key":"12_CR6","unstructured":"Gao, J., et al.: Get3d: a generative model of high quality 3d textured shapes learned from images. NeurIPS (2022)"},{"issue":"5","key":"12_CR7","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.11834\/jig.220695","volume":"28","author":"S Gaoli","year":"2023","unstructured":"Gaoli, S., Shudi, X., Qijun, Z.: Soft threshold denoising and video data fusion-relevant low-quality 3d face recognition. J. Image Graph. 28(5), 1434\u20131444 (2023)","journal-title":"J. Image Graph."},{"issue":"1","key":"12_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/106365603321828970","volume":"11","author":"N Hansen","year":"2003","unstructured":"Hansen, N., M\u00fcller, S.D., Koumoutsakos, P.: Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (cma-es). Evol. Comput. 11(1), 1\u201318 (2003)","journal-title":"Evol. Comput."},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Van\u00a0den Heuvel, F.A.: 3D reconstruction from a single image using geometric constraints. ISPRS (1998)","DOI":"10.1016\/S0924-2716(98)00019-7"},{"key":"12_CR10","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Ju, T., Losasso, F., Schaefer, S., Warren, J.: Dual contouring of hermite data. In: TOG (2002)","DOI":"10.1145\/566570.566586"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Khilar, R., Chitrakala, S., SelvamParvathy, S.: 3D image reconstruction: techniques, applications and challenges. In: ICOSS (2013)","DOI":"10.1109\/ICOISS.2013.6678395"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Koutsoudis, A., Vidmar, B., Ioannakis, G., Arnaoutoglou, F., Pavlidis, G., Chamzas, C.: Multi-image 3D reconstruction data evaluation. JCH (2014)","DOI":"10.1016\/j.culher.2012.12.003"},{"key":"12_CR14","unstructured":"Kwon, M., Jeong, J., Uh, Y.: Diffusion models already have a semantic latent space. In: ICLR (2023)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Laine, S., Hellsten, J., Karras, T., Seol, Y., Lehtinen, J., Aila, T.: Modular primitives for high-performance differentiable rendering. TOG (2020)","DOI":"10.1145\/3414685.3417861"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Liao, Y., Donne, S., Geiger, A.: Deep marching cubes: Learning explicit surface representations. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00308"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: High-resolution text-to-3D content creation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. In: SIGGRAPH (1987)","DOI":"10.1145\/37401.37422"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Melas-Kyriazi, L., Laina, I., Rupprecht, C., Vedaldi, A.: Realfusion: 360deg reconstruction of any object from a single image. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"12_CR20","doi-asserted-by":"crossref","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. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. TOG (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Munkberg, J., et al.: Extracting triangular 3d models, materials, and lighting from images. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00810"},{"key":"12_CR23","unstructured":"Nielson, G.M.: Dual marching cubes. In: IEEE Visualization 2004 (2004)"},{"key":"12_CR24","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. In: ICLR (2023)"},{"key":"12_CR25","unstructured":"Qian, G., et al.: Magic123: One image to high-quality 3D object generation using both 2D and 3D diffusion priors. In: ICLR (2024)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: U2-net: Going deeper with nested u-structure for salient object detection. Pattern Recogn. 106, 107404 (2020)","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"12_CR27","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Rechenberg, I.: Evolution strategy: nature\u2019s way of optimization. In: Optimization: Methods and Applications, Possibilities and Limitations (1989)","DOI":"10.1007\/978-3-642-83814-9_6"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR30","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et\u00a0al.: Laion-5b: an open large-scale dataset for training next generation image-text models. NeurIPS (2022)"},{"key":"12_CR31","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. In: NeurIPS (2021)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Shen, T., et al.: Flexible isosurface extraction for gradient-based mesh optimization. TOG (2023)","DOI":"10.1145\/3592430"},{"key":"12_CR33","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Su, P., Zhao, Q., Pan, F., Gao, F.: Cascaded network-based single-view bird 3d reconstruction. In: ICANN (2023)","DOI":"10.1007\/978-3-031-44210-0_10"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Sun, S., Zhu, Z., Dai, X., Zhao, Q., Li, J.: Weakly-supervised reconstruction of 3d objects with large shape variation from single in-the-wild images. In: ACCV (2020)","DOI":"10.1007\/978-3-030-69525-5_1"},{"key":"12_CR36","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3D content creation. In: ICLR (2024)"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Make-it-3D: High-fidelity 3D creation from a single image with diffusion prior. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score jacobian chaining: lifting pretrained 2D diffusion models for 3D generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Wang, R., Liu, Y., Su, P., Zhang, J., Zhao, Q.: 3d semantic subspace traverser: empowering 3d generative model with shape editing capability. In: CVPR (2023)","DOI":"10.1109\/ICCV51070.2023.01325"},{"key":"12_CR40","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: NeurIPS (2024)"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"12_CR42","unstructured":"Zhao, B.N., et al.: Dreamdistribution: prompt distribution learning for text-to-image diffusion models (2023). arXiv:2312.14216"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8508-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:13:38Z","timestamp":1730528018000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8508-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785070","9789819785087"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8508-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}