{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:14:21Z","timestamp":1767323661257,"version":"3.48.0"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557363","type":"print"},{"value":"9789819557370","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5737-0_21","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:09:56Z","timestamp":1767323396000},"page":"292-306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MVD-HuGaS: Human Gaussians from\u00a0a\u00a0Single Image via\u00a03D Human Multi-View Diffusion Prior"],"prefix":"10.1007","author":[{"given":"Kaiqiang","family":"Xiong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbo","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huachen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"AlBahar, B., Saito, S., Tseng, H.Y., Kim, C., Kopf, J., Huang, J.B.: Single-image 3d human digitization with shape-guided diffusion. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201311 (2023)","DOI":"10.1145\/3610548.3618153"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Zanfir, M., Sminchisescu, C.: Photorealistic monocular 3d reconstruction of humans wearing clothing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1506\u20131515 (2022)","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Bian, W., Wang, Z., Li, K., Bian, J.W., Prisacariu, V.A.: NoPe-NeRF: optimising neural radiance field with no pose prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4160\u20134169 (2023)","DOI":"10.1109\/CVPR52729.2023.00405"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In: Seminal Graphics Papers: Pushing the Boundaries, vol. 2, pp. 157\u2013164. ACM (2023)","DOI":"10.1145\/3596711.3596730"},{"key":"21_CR5","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Cai, Z., et\u00a0al.: HuMMan: multi-modal 4D human dataset for versatile sensing and modeling. In: European Conference on Computer Vision, pp. 557\u2013577. Springer (2022)","DOI":"10.1007\/978-3-031-20071-7_33"},{"issue":"3","key":"21_CR7","first-page":"413","volume":"20","author":"C Cao","year":"2013","unstructured":"Cao, C., Weng, Y., Zhou, S., Tong, Y., Zhou, K.: FacewareHouse: a 3D facial expression database for visual computing. IEEE Trans. Visual Comput. Graphics 20(3), 413\u2013425 (2013)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Corona, E., Zanfir, M., Alldieck, T., Bazavan, E.G., Zanfir, A., Sminchisescu, C.: Structured 3d features for reconstructing controllable avatars. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16954\u201316964 (2023)","DOI":"10.1109\/CVPR52729.2023.01626"},{"key":"21_CR9","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":"21_CR10","doi-asserted-by":"crossref","unstructured":"Feng, Y., Choutas, V., Bolkart, T., Tzionas, D., Black, M.J.: Collaborative regression of expressive bodies using moderation. In: 2021 International Conference on 3D Vision (3DV), pp. 792\u2013804. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00088"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Gao, X., et al.: Contex-human: free-view rendering of human from a single image with texture-consistent synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10084\u201310094 (2024)","DOI":"10.1109\/CVPR52733.2024.00961"},{"key":"21_CR12","doi-asserted-by":"publisher","first-page":"3815","DOI":"10.1109\/TIP.2021.3065798","volume":"30","author":"Y Guo","year":"2021","unstructured":"Guo, Y., Cai, L., Zhang, J.: 3d face from X: learning face shape from diverse sources. IEEE Trans. Image Process. 30, 3815\u20133827 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Han, S.H., Park, M.G., Yoon, J.H., Kang, J.M., Park, Y.J., Jeon, H.G.: High-fidelity 3D human digitization from single 2k resolution images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12869\u201312879 (2023)","DOI":"10.1109\/CVPR52729.2023.01237"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Ho, I., Song, J., Hilliges, O., et\u00a0al.: SiTH: single-view textured human reconstruction with image-conditioned diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 538\u2013549 (2024)","DOI":"10.1109\/CVPR52733.2024.00058"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: One-shot implicit animatable avatars with model-based priors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8974\u20138985 (2023)","DOI":"10.1109\/ICCV51070.2023.00824"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Tech: text-guided reconstruction of lifelike clothed humans. In: 2024 International Conference on 3D Vision (3DV), pp. 1531\u20131542. IEEE (2024)","DOI":"10.1109\/3DV62453.2024.00152"},{"key":"21_CR17","first-page":"26565","volume":"35","author":"T Karras","year":"2022","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. Adv. Neural. Inf. Process. Syst. 35, 26565\u201326577 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"21_CR18","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":"21_CR19","doi-asserted-by":"crossref","unstructured":"Liao, T., et al.: High-fidelity clothed avatar reconstruction from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8662\u20138672 (2023)","DOI":"10.1109\/CVPR52729.2023.00837"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Ma, W.C., Torralba, A., Lucey, S.: BARF: bundle-adjusting neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5741\u20135751 (2021)","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"21_CR21","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10072\u201310083 (2024)","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"21_CR22","unstructured":"Liu, M., et al.: One-2-3-45: any single image to 3d mesh in 45 seconds without per-shape optimization. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"21_CR23","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":"21_CR24","unstructured":"Liu, Y., et al.: SyncDreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Long, X., et\u00a0al.: Wonder3D: single image to 3D using cross-domain diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9970\u20139980 (2024)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. In: Seminal Graphics Papers: Pushing the Boundaries, vol. 2, pp. 851\u2013866. ACM (2023)","DOI":"10.1145\/3596711.3596800"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Peng, R., Wang, R., Wang, Z., Lai, Y., Wang, R.: Rethinking depth estimation for multi-view stereo: a unified representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8645\u20138654 (2022)","DOI":"10.1109\/CVPR52688.2022.00845"},{"key":"21_CR29","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"21_CR30","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":"21_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":"21_CR32","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: PIFu: pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2304\u20132314 (2019)","DOI":"10.1109\/ICCV.2019.00239"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Saito, S., Simon, T., Saragih, J., Joo, H.: PIFuHD: multi-level pixel-aligned implicit function for high-resolution 3d human digitization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 84\u201393 (2020)","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"21_CR35","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)"},{"key":"21_CR36","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. arXiv preprint arXiv:2403.12008 (2024)","DOI":"10.1007\/978-3-031-73232-4_25"},{"issue":"4","key":"21_CR37","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","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. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR38","unstructured":"Weng, H., et al.: Consistent123: improve consistency for one image to 3D object synthesis. arXiv preprint arXiv:2310.08092 (2023)"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Xiu, Y., Yang, J., Cao, X., Tzionas, D., Black, M.J.: ECON: explicit clothed humans optimized via normal integration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 512\u2013523 (2023)","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Xiu, Y., Yang, J., Tzionas, D., Black, M.J.: ICON: implicit clothed humans obtained from normals. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13286\u201313296. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"21_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1007\/978-3-030-01237-3_47","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Yao","year":"2018","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: depth inference for unstructured multi-view stereo. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 785\u2013801. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_47"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Yu, T., Zheng, Z., Guo, K., Liu, P., Dai, Q., Liu, Y.: Function4d: real-time human volumetric capture from very sparse consumer RGBD sensors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5746\u20135756 (2021)","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Yu, Z., Chen, A., Huang, B., Sattler, T., Geiger, A.: Mip-splatting: Alias-free 3d gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19447\u201319456 (2024)","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, X., Zhang, Q., Cao, Y., Shan, Y., Liao, J.: HumanRef: single image to 3d human generation via reference-guided diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1844\u20131854 (2024)","DOI":"10.1109\/CVPR52733.2024.00181"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Yang, Z., Yang, Y.: SIFU: side-view conditioned implicit function for real-world usable clothed human reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9936\u20139947 (2024)","DOI":"10.1109\/CVPR52733.2024.00948"},{"issue":"6","key":"21_CR46","doi-asserted-by":"publisher","first-page":"3170","DOI":"10.1109\/TPAMI.2021.3050505","volume":"44","author":"Z Zheng","year":"2021","unstructured":"Zheng, Z., Yu, T., Liu, Y., Dai, Q.: PaMIR: parametric model-conditioned implicit representation for image-based human reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3170\u20133184 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"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\/978-981-95-5737-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:10:01Z","timestamp":1767323401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5737-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557363","9789819557370"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5737-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","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":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}