{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:55:13Z","timestamp":1783439713128,"version":"3.54.6"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727504","type":"print"},{"value":"9783031727511","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72751-1_4","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T09:52:13Z","timestamp":1729849933000},"page":"57-74","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":105,"title":["CRM: Single Image to\u00a03D Textured Mesh with\u00a0Convolutional Reconstruction Model"],"prefix":"10.1007","author":[{"given":"Zhengyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yikai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chendong","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dajiang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongxuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Bao, F., et al.: All are worth words: a VIT backbone for diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"4_CR2","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"4_CR3","unstructured":"Brown, T.B., et al.: Language models are few-shot learners (2020)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et\u00a0al.: Efficient geometry-aware 3d generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16123\u201316133 (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"4_CR5","doi-asserted-by":"publisher","unstructured":"Chen, A., Xu, Z., Geiger, A., Yu, J., Su, H.: TensoRF: tensorial radiance fields. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXXII, pp. 333\u2013350. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_20","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Single-stage diffusion nerf: a unified approach to 3d generation and reconstruction. arXiv preprint arXiv:2304.06714 (2023)","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"4_CR7","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. arXiv preprint arXiv:2303.13873 (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: IT3D: improved text-to-3D generation with explicit view synthesis. Proc. AAAI Conf. Artif. Intell. 38(2), 1237\u20131244 (2024)","DOI":"10.1609\/aaai.v38i2.27886"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, F., Liu, H.: Text-to-3D using Gaussian splatting. arXiv preprint arXiv:2309.16585 (2023)","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, Y.C., Lee, H.Y., Tuyakov, S., Schwing, A., Gui, L.: SDFusion: multimodal 3d shape completion, reconstruction, and generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Decatur, D., Lang, I., Aberman, K., Hanocka, R.: 3D paintbrush: local stylization of 3d shapes with cascaded score distillation. arXiv preprint arXiv:2311.09571 (2023)","DOI":"10.1109\/CVPR52733.2024.00428"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Deitke, M., et\u00a0al.: Objaverse-xl: a universe of 10m+ 3d objects. Adv. Neural Inf. Process. Syst. 36 (2024)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Downs, L., et al.: Google scanned objects: a high-quality dataset of 3d scanned household items. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 2553\u20132560. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"4_CR15","unstructured":"Gao, J., et al.: Get3d: a generative model of high quality 3d textured shapes learned from images. Adv. Neural. Inf. Process. Syst. 35, 31841\u201331854 (2022)"},{"key":"4_CR16","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":"4_CR17","unstructured":"He, Z., Wang, T.: Openlrm: open-source large reconstruction models (2023). https:\/\/github.com\/3DTopia\/OpenLRM"},{"key":"4_CR18","unstructured":"Hong, Y., et al.: LRM: large reconstruction model for single image to 3D. arXiv preprint arXiv:2311.04400 (2023)"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023)","DOI":"10.1145\/3592433"},{"key":"4_CR20","unstructured":"Kim, S., Lee, K., Choi, J.S., Jeong, J., Sohn, K., Shin, J.: Collaborative score distillation for consistent visual synthesis (2023)"},{"key":"4_CR21","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":"4_CR22","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":"4_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: FocalDreamer: text-driven 3D editing via focal-fusion assembly. Proc. AAAI Conf. Artif. Intell. 38(4), 3279\u20133287 (2024)","DOI":"10.1609\/aaai.v38i4.28113"},{"key":"4_CR24","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 (2023)","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"4_CR25","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, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Lin, S., Liu, B., Li, J., Yang, X.: Common diffusion noise schedules and sample steps are flawed. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5404\u20135411 (2024)","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"4_CR27","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 (2023)","DOI":"10.1109\/CVPR52733.2024.01962"},{"key":"4_CR28","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. arXiv preprint arXiv:2311.07885 (2023)","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"4_CR29","unstructured":"Liu, M., et\u00a0al.: One-2-3-45: any single image to 3d mesh in 45 seconds without per-shape optimization. arXiv preprint arXiv:2306.16928 (2023)"},{"key":"4_CR30","doi-asserted-by":"crossref","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 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"4_CR31","unstructured":"Liu, Y., et al.: Syncdreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Long, X., et\u00a0al.: Wonder3d: single image to 3D using cross-domain diffusion. arXiv preprint arXiv:2310.15008 (2023)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Lorraine, J., et al.: Att3d: amortized text-to-3D object synthesis (2023)","DOI":"10.1109\/ICCV51070.2023.01645"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Direct2.5: diverse text-to-3d generation via multi-view 2.5d diffusion (2023)","DOI":"10.1109\/CVPR52733.2024.00835"},{"key":"4_CR35","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)"},{"key":"4_CR36","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. Commun. ACM 65(1), 99\u2013106 (2021)","DOI":"10.1145\/3503250"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Nielson, G.M.: Dual marching cubes. In: IEEE Visualization 2004, pp. 489\u2013496. IEEE (2004)","DOI":"10.1109\/VISUAL.2004.28"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"4_CR39","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"4_CR40","unstructured":"Qian, G., et al.: Atom: amortized text-to-mesh using 2D diffusion (2024)"},{"key":"4_CR41","unstructured":"Qian, G., et al.: Magic123: one image to high-quality 3D object generation using both 2D and 3D diffusion priors (2023)"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Qiu, L., et al.: Richdreamer: a generalizable normal-depth diffusion model for detail richness in text-to-3D (2023)","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"4_CR43","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"4_CR44","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":"4_CR45","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)"},{"key":"4_CR46","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models (2022)"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Shen, T., et al.: Flexible isosurface extraction for gradient-based mesh optimization. ACM Trans. Graph. 42(4), 1\u201316 (2023)","DOI":"10.1145\/3592430"},{"key":"4_CR48","unstructured":"Shi, R., Wei, X., Wang, C., Su, H.: Zerorf: fast sparse view 360 $$\\{$$$$\\backslash $$deg$$\\}$$ reconstruction with zero pretraining. arXiv preprint arXiv:2312.09249 (2023)"},{"key":"4_CR49","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":"4_CR50","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"4_CR51","unstructured":"Sun, J., et al.: Dreamcraft3d: hierarchical 3d generation with bootstrapped diffusion prior (2023)"},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Tang, J., Chen, Z., Chen, X., Wang, T., Zeng, G., Liu, Z.: LGM: large multi-view Gaussian model for high-resolution 3D content creation (2024)","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"4_CR53","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":"4_CR54","unstructured":"Tochilkin, D., et al.: Triposr: fast 3D object reconstruction from a single image. arXiv preprint arXiv:2403.02151 (2024)"},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Tsalicoglou, C., Manhardt, F., Tonioni, A., Niemeyer, M., Tombari, F.: Textmesh: generation of realistic 3D meshes from text prompts. arXiv preprint arXiv:2304.12439 (2023)","DOI":"10.1109\/3DV62453.2024.00154"},{"key":"4_CR56","unstructured":"Vaswani, A., et al.: Attention is all you need (2023)"},{"key":"4_CR57","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 (2022)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"4_CR58","doi-asserted-by":"crossref","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: Neus: learning neural implicit surfaces by volume rendering for multi-view reconstruction (2023)","DOI":"10.1109\/ICCV51070.2023.00305"},{"key":"4_CR59","unstructured":"Wang, P., Shi, Y.: Imagedream: image-prompt multi-view diffusion for 3D generation. arXiv preprint arXiv:2312.02201 (2023)"},{"key":"4_CR60","unstructured":"Wang, P., et al.: PF-LRM: pose-free large reconstruction model for joint pose and shape prediction. arXiv preprint arXiv:2311.12024 (2023)"},{"key":"4_CR61","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: Rodin: a generative model for sculpting 3D digital avatars using diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4563\u20134573 (2023)","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"4_CR62","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Animatabledreamer: text-guided non-rigid 3D model generation and reconstruction with canonical score distillation (2023)","DOI":"10.1007\/978-3-031-72698-9_19"},{"key":"4_CR63","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: Thirty-seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=ppJuFSOAnM"},{"key":"4_CR64","unstructured":"Xu, Y., et al.: Dmv3d: denoising multi-view diffusion using 3d large reconstruction model. arXiv preprint arXiv:2311.09217 (2023)"},{"key":"4_CR65","unstructured":"Yu, X., Guo, Y.C., Li, Y., Liang, D., Zhang, S.H., Qi, X.: Text-to-3D with classifier score distillation (2023)"},{"key":"4_CR66","unstructured":"Zeng, X., Vahdat, A., Williams, F., Gojcic, Z., Litany, O., Fidler, S., Kreis, K.: Lion: latent point diffusion models for 3D shape generation (2022)"},{"key":"4_CR67","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 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"4_CR68","doi-asserted-by":"crossref","unstructured":"Zheng, X.Y., Pan, H., Guo, Y.X., Tong, X., Liu, Y.: Mvd$$^2$$: efficient multiview 3D reconstruction for multiview diffusion (2024)","DOI":"10.1145\/3641519.3657403"},{"key":"4_CR69","doi-asserted-by":"crossref","unstructured":"Zheng, X.Y., Pan, H., Wang, P.S., Tong, X., Liu, Y., Shum, H.Y.: Locally attentional SDF diffusion for controllable 3D shape generation. arXiv preprint arXiv:2305.04461 (2023)","DOI":"10.1145\/3592103"},{"key":"4_CR70","unstructured":"Zhu, J., Zhuang, P.: Hifa: high-fidelity text-to-3d generation with advanced diffusion guidance (2023)"},{"key":"4_CR71","doi-asserted-by":"crossref","unstructured":"Zou, Z.X., et al.: Triplane meets gaussian splatting: Fast and generalizable single-view 3d reconstruction with transformers. arXiv preprint arXiv:2312.09147 (2023)","DOI":"10.1109\/CVPR52733.2024.00983"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72751-1_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T07:48:10Z","timestamp":1732952890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72751-1_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031727504","9783031727511"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72751-1_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}