{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T04:48:27Z","timestamp":1751690907567,"version":"3.40.3"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726699"},{"type":"electronic","value":"9783031726705"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72670-5_23","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"405-421","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Vista3D: Unravel the\u00a03D Darkside of\u00a0a\u00a0Single Image"],"prefix":"10.1007","author":[{"given":"Qiuhong","family":"Shen","sequence":"first","affiliation":[]},{"given":"Xingyi","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Michael Bi","family":"Mi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0057-1404","authenticated-orcid":false,"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"23_CR1","unstructured":"Cao, Z., Hong, F., Wu, T., Pan, L., Liu, Z.: Large-vocabulary 3D diffusion model with transformer. arXiv preprint arXiv:2309.07920 (2023)"},{"key":"23_CR2","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 (October 2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"23_CR3","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":"23_CR4","unstructured":"Chung, J., Lee, S., Nam, H., Lee, J., Lee, K.M.: LucidDreamer: domain-free generation of 3D gaussian splatting scenes. arXiv preprint arXiv:2311.13384 (2023)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Deitke, M., et\u00a0al.: Objaverse-XL: a universe of 10M+ 3D objects. arXiv preprint arXiv:2307.05663 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: CVPR, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"23_CR7","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":"23_CR8","doi-asserted-by":"crossref","unstructured":"Duggal, S., Pathak, D.: Topologically-aware deformation fields for single-view 3D reconstruction. In: CVPR, pp. 1536\u20131546 (2022)","DOI":"10.1109\/CVPR52688.2022.00159"},{"key":"23_CR9","unstructured":"Hong, Y., et al.: LRM: large reconstruction model for single image to 3D. arXiv preprint arXiv:2311.04400 (2023)"},{"key":"23_CR10","unstructured":"Huang, Y., Wang, J., Shi, Y., Qi, X., Zha, Z.J., Zhang, L.: DreamTime: an improved optimization strategy for text-to-3D content creation. arXiv preprint arXiv:2306.12422 (2023)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields. In: CVPR, pp. 857\u2013866. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"23_CR12","unstructured":"Jun, H., Nichol, A.: Shap-E: generating conditional 3D implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Transactions on Graphics 42(4) (July 2023), https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"23_CR14","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. In: CVPR, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"23_CR16","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 (2023)","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"23_CR17","unstructured":"Liu, M., Xu, C., Jin, H., Chen, L., Xu, Z., Su, H., 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":"23_CR18","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3d object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"23_CR19","unstructured":"Liu, Y., et al.: SyncDreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"23_CR20","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":"23_CR21","doi-asserted-by":"crossref","unstructured":"Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. In: Seminal Graphics: Pioneering Efforts that Shaped the Field, pp. 347\u2013353 (1998)","DOI":"10.1145\/280811.281026"},{"key":"23_CR22","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, pp. 8446\u20138455 (2023)","DOI":"10.1109\/CVPR52729.2023.00816"},{"issue":"1","key":"23_CR23","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"},{"issue":"4","key":"23_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. (ToG) 41(4), 1\u201315 (2022)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"23_CR25","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":"23_CR26","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":"23_CR27","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: Text-to-3D using 2D diffusion. In: ICLR. OpenReview.net (2023)"},{"key":"23_CR28","unstructured":"Qian, G., et\u00a0al.: Magic123: one image to high-quality 3D object generation using both 2D and 3D diffusion priors. arXiv preprint arXiv:2306.17843 (2023)"},{"key":"23_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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Sargent, K., et\u00a0al.: ZeroNVS: Zero-shot 360-degree view synthesis from a single real image. arXiv preprint arXiv:2310.17994 (2023)","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"23_CR31","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":"23_CR32","unstructured":"Shen, Q., Yang, X., Wang, X.: Anything-3D: towards single-view anything reconstruction in the wild (2023)"},{"key":"23_CR33","unstructured":"Shen, Q., et al.: Gamba: marry gaussian splatting with mamba for single view 3D reconstruction. arXiv preprint arXiv:2403.18795 (2024)"},{"key":"23_CR34","first-page":"6087","volume":"34","author":"T Shen","year":"2021","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. Adv. Neural. Inf. Process. Syst. 34, 6087\u20136101 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"23_CR35","first-page":"1","volume":"42","author":"T Shen","year":"2023","unstructured":"Shen, T., et al.: Flexible Isosurface extraction for gradient-based mesh optimization. ACM Trans. Graph. 42(4), 1\u201316 (2023)","journal-title":"ACM Trans. Graph."},{"key":"23_CR36","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)"},{"key":"23_CR37","unstructured":"Sun, J., et al.: Dreamcraft3D: hierarchical 3D generation with bootstrapped diffusion prior. arXiv preprint arXiv:2310.16818 (2023)"},{"key":"23_CR38","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":"23_CR39","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, pp. 22819\u201322829 (October 2023)","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"23_CR40","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, pp. 12619\u201312629 (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"23_CR41","doi-asserted-by":"crossref","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9892\u20139902 (2024)","DOI":"10.1109\/CVPR52733.2024.00944"},{"key":"23_CR42","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":"23_CR43","unstructured":"Xu, Y., et\u00a0al.: DMV3D: denoising multi-view diffusion using 3D large reconstruction model. arXiv preprint arXiv:2311.09217 (2023)"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Yang, X., Wang, X.: Hash3D: training-free acceleration for 3D generation. arXiv preprint arXiv:2404.06091 (2024)","DOI":"10.36227\/techrxiv.171208938.83786646\/v1"},{"key":"23_CR45","unstructured":"Yi, T., et al.: GaussianDreamer: fast generation from text to 3D Gaussian splatting with point cloud priors. arXiv preprint arXiv:2310.08529 (2023)"},{"key":"23_CR46","unstructured":"Yi, X., Wu, Z., Shen, Q., Xu, Q., Zhou, P., Lim, J.H., Yan, S., Wang, X., Zhang, H.: MVGamba: unify 3D content generation as state space sequence modeling. arXiv preprint arXiv:2406.06367 (2024)"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Yi, X., Wu, Z., Xu, Q., Zhou, P., Lim, J.H., Zhang, H.: Diffusion time-step curriculum for one image to 3D generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9948\u20139958 (2024)","DOI":"10.1109\/CVPR52733.2024.00949"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: pixelNERF: neural radiance fields from one or few images. In: CVPR, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"23_CR49","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":"23_CR50","doi-asserted-by":"crossref","unstructured":"Zou, Z.X., et al.: Triplane meets gaussian splatting: fast and generalizable single-view 3D reconstruction with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10324\u201310335 (2024)","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\/978-3-031-72670-5_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:20:35Z","timestamp":1732828835000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72670-5_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726699","9783031726705"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72670-5_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}