{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T22:35:29Z","timestamp":1769121329642,"version":"3.49.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726392","type":"print"},{"value":"9783031726408","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72640-8_10","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"175-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["MVDiffusion++: A Dense High-Resolution Multi-view Diffusion Model for\u00a0Single or\u00a0Sparse-View 3D Object Reconstruction"],"prefix":"10.1007","author":[{"given":"Shitao","family":"Tang","sequence":"first","affiliation":[]},{"given":"Jiacheng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Dilin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chengzhou","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Fuyang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yuchen","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Vikas","family":"Chandra","sequence":"additional","affiliation":[]},{"given":"Yasutaka","family":"Furukawa","sequence":"additional","affiliation":[]},{"given":"Rakesh","family":"Ranjan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"issue":"10","key":"10_CR1","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/2001269.2001293","volume":"54","author":"S Agarwal","year":"2011","unstructured":"Agarwal, S., et al.: Building Rome in a day. Commun. ACM 54(10), 105\u2013112 (2011)","journal-title":"Commun. ACM"},{"key":"10_CR2","unstructured":"Dao, T.: Flashattention-2: faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)"},{"key":"10_CR3","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: fast and memory-efficient exact attention with IO-awareness. In: Advances in Neural Information Processing Systems, vol. 35, pp. 16344\u201316359 (2022)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Downs, L., et al.: Google scanned objects: a high-quality dataset of 3D scanned household items. In: ICRA (2022)","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Eftekhar, A., Sax, A., Malik, J., Zamir, A.: Omnidata: a scalable pipeline for making multi-task mid-level vision datasets from 3D scans. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10786\u201310796 (2021)","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Furukawa, Y., Curless, B., Seitz, S.M., Szeliski, R.: Towards internet-scale multi-view stereo. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1434\u20131441. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539802"},{"key":"10_CR7","unstructured":"Guo, Y.C.: Instant neural surface reconstruction (2022). https:\/\/github.com\/bennyguo\/instant-nsr-pl"},{"key":"10_CR8","unstructured":"He, Z., Wang, T.: Openlrm: open-source large reconstruction models (2023). https:\/\/github.com\/3DTopia\/OpenLRM"},{"key":"10_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"10_CR10","unstructured":"Hong, Y., et al.: LRM: large reconstruction model for single image to 3D. arXiv preprint arXiv:2311.04400 (2023)"},{"key":"10_CR11","unstructured":"Jiang, H., Jiang, Z., Zhao, Y., Huang, Q.: Leap: liberate sparse-view 3D modeling from camera poses. arXiv preprint arXiv:2310.01410 (2023)"},{"key":"10_CR12","unstructured":"Jun, H., Nichol, A.: Shap-e: generating conditional 3D implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Neuralangelo: high-fidelity neural surface reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8456\u20138465 (2023)","DOI":"10.1109\/CVPR52729.2023.00817"},{"key":"10_CR14","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":"10_CR15","unstructured":"Liu, M., Xu, C., Jin, H., Chen, L., Xu, Z., Su, H.: One-2-3-45: any single image to 3D mesh in 45 seconds without per-shape optimization. arXiv preprint arXiv:2306.16928 (2023)"},{"key":"10_CR16","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: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"10_CR17","unstructured":"Liu, Y., et al.: Syncdreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Long, X., et al.: Wonder3d: single image to 3D using cross-domain diffusion. arXiv preprint arXiv:2310.15008 (2023)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"10_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":"10_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":"10_CR21","doi-asserted-by":"crossref","unstructured":"Mittal, P., Cheng, Y.C., Singh, M., Tulsiani, S.: Autosdf: shape priors for 3D completion, reconstruction and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 306\u2013315 (2022)","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Murray, N., Marchesotti, L., Perronnin, F.: Ava: a large-scale database for aesthetic visual analysis. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2408\u20132415. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"10_CR23","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":"10_CR24","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"10_CR25","unstructured":"Qian, G., et al.: Magic123: one image to high-quality 3D object generation using both 2D and 3D diffusion priors. arXiv preprint arXiv:2306.17843 (2023)"},{"key":"10_CR26","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512 (2022)"},{"key":"10_CR27","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)"},{"key":"10_CR28","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":"10_CR29","doi-asserted-by":"crossref","unstructured":"Stereopsis, R.M.: Accurate, dense, and robust multiview stereopsis. IEEE Trans. Pattern Anal. Mach. Intell. 32(8) (2010)","DOI":"10.1109\/TPAMI.2009.161"},{"key":"10_CR30","unstructured":"Tang, S., Zhang, F., Chen, J., Wang, P., Furukawa, Y.: Mvdiffusion: enabling holistic multi-view image generation with correspondence-aware diffusion. arXiv preprint arXiv:2307.01097 (2023)"},{"key":"10_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"10_CR32","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-031-19824-3_9","volume-title":"ECCV 2022","author":"J Wang","year":"2022","unstructured":"Wang, J., et al.: Neuris: neural reconstruction of indoor scenes using normal priors. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13692, pp. 139\u2013155. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_9"},{"key":"10_CR33","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. In: NeurIPS (2021)"},{"key":"10_CR34","unstructured":"Wang, P., Shi, Y.: Imagedream: image-prompt multi-view diffusion for 3D generation. arXiv preprint arXiv:2312.02201 (2023)"},{"key":"10_CR35","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":"10_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lira, W., Wang, W., Mahdavi-Amiri, A., Zhang, H.: Slice3d: multi-slice, occlusion-revealing, single view 3D reconstruction. arXiv preprint arXiv:2312.02221 (2023)","DOI":"10.1109\/CVPR52733.2024.00943"},{"issue":"4","key":"10_CR37","first-page":"600","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. TIP 13(4), 600\u2013612 (2004)","journal-title":"TIP"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Wu, T., et al.: Omniobject3d: large-vocabulary 3D object dataset for realistic perception, reconstruction and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 803\u2013814 (2023)","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"10_CR39","unstructured":"Xu, Y., et al.: Dmv3d: denoising multi-view diffusion using 3D large reconstruction model. arXiv preprint arXiv:2311.09217 (2023)"},{"key":"10_CR40","unstructured":"Yan, X., Yang, J., Yumer, E., Guo, Y., Lee, H.: Perspective transformer nets: learning single-view 3D object reconstruction without 3D supervision. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Yang, Z., Ren, Z., Bautista, M.A., Zhang, Z., Shan, Q., Huang, Q.: Fvor: robust joint shape and pose optimization for few-view object reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2497\u20132507 (2022)","DOI":"10.1109\/CVPR52688.2022.00253"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: Mvsnet: depth inference for unstructured multi-view stereo. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"10_CR43","unstructured":"Yu, Z., Peng, S., Niemeyer, M., Sattler, T., Geiger, A.: Monosdf: exploring monocular geometric cues for neural implicit surface reconstruction. In: Advances in Neural Information Processing Systems, vol. 35, pp. 25018\u201325032 (2022)"},{"key":"10_CR44","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"}],"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\/978-3-031-72640-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:46:11Z","timestamp":1730108771000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72640-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031726392","9783031726408"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72640-8_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 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"}}]}}