{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:16:06Z","timestamp":1775578566164,"version":"3.50.1"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T00:00:00Z","timestamp":1733961600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T00:00:00Z","timestamp":1733961600000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11263-024-02310-5","type":"journal-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T06:45:36Z","timestamp":1733985936000},"page":"2825-2844","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MoDA: Modeling Deformable 3D Objects from Casual Videos"],"prefix":"10.1007","volume":"133","author":[{"given":"Chaoyue","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiacheng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiwen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuan-Sheng","family":"Foo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fayao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0329-7458","authenticated-orcid":false,"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,12]]},"reference":[{"key":"2310_CR1","doi-asserted-by":"crossref","unstructured":"Badger, M., Wang, Y., Modh, A., Perkes, A., Kolotouros, N., Pfrommer, B. G., Schmidt, M. F., & Daniilidis, K. (2020). 3D bird reconstruction: A dataset, model, and shape recovery from a single view. In European Conference on Computer Vision (pp. 1\u201317)","DOI":"10.1007\/978-3-030-58523-5_1"},{"key":"2310_CR2","doi-asserted-by":"crossref","unstructured":"Biggs, B., Boyne, O., Charles, J., Fitzgibbon, A., & Cipolla, R. (2020). Who left the dogs out? 3D animal reconstruction with expectation maximization in the loop. In European Conference on Computer Vision (pp. 195\u2013211).","DOI":"10.1007\/978-3-030-58621-8_12"},{"key":"2310_CR3","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Zhao, F., Zhang, X., Xiang, F., Yu, J., & Su, H. (2021). MVSNeRF: Fast generalizable radiance field reconstruction from multi-view stereo. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 14124\u201314133).","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"2310_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Yang, X., Yang, F., Feng, C., Fu, Z., Foo, C.S., Lin, G., & Liu, F. (2024). Sculpt3D: Multi-view consistent text-to-3D generation with sparse 3D prior. arXiv Preprint arXiv:2403.09140.","DOI":"10.1109\/CVPR52733.2024.00974"},{"key":"2310_CR5","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., & Guibas, L. J. (2017). A point set generation network for 3D object reconstruction from a single image. iN Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 605\u2013613).","DOI":"10.1109\/CVPR.2017.264"},{"key":"2310_CR6","doi-asserted-by":"crossref","unstructured":"Goel, S., Kanazawa, A., & Malik, J. (2020). Shape and viewpoint without keypoints. In European Conference on Computer Vision (pp. 88\u2013104)","DOI":"10.1007\/978-3-030-58555-6_6"},{"key":"2310_CR7","unstructured":"Gropp, A., Yariv, L., Haim, N., Atzmon, M., Lipman, Y. (2020). Implicit geometric regularization for learning shapes. arXiv Preprint arXiv:2002.10099."},{"key":"2310_CR8","unstructured":"Hejl, J. (2004). Hardware skinning with quaternions. In A. Kirmse (Ed.), Game programming Gems 4 (pp. 487\u2013495). Charles River Media. 487\u2013495."},{"key":"2310_CR9","doi-asserted-by":"crossref","unstructured":"Henzler, P., Reizenstein, J., Labatut, P., Shapovalov, R., Ritschel, T., Vedaldi, A., & Novotny, D. (2021). Unsupervised learning of 3D object categories from videos in the wild. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 4700\u20134709).","DOI":"10.1109\/CVPR46437.2021.00467"},{"key":"2310_CR10","doi-asserted-by":"crossref","unstructured":"Jacobson, A., Deng, Z., Kavan, L., & Lewis, J. P. (2014). Skinning: Real-time shape deformation (full text not available). ACM SIGGRAPH Courses (p. 1).","DOI":"10.1145\/2659467.2675048"},{"key":"2310_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, W., Yi, K. M., Samei, G., Tuzel, O., & Ranjan, A. (2022). NeuMan: Neural human radiance field from a single video. arxiv Preprint arXiv:2203.12575.","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"2310_CR12","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Tulsiani, S., Efros, A. A., & Malik, J. (2018). Learning category-specific mesh reconstruction from image collections. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 371\u2013386).","DOI":"10.1007\/978-3-030-01267-0_23"},{"key":"2310_CR13","doi-asserted-by":"crossref","unstructured":"Kavan, L., Collins, S., \u017d\u00e1ra, J., & O\u2019Sullivan, C. (2007). Skinning with dual quaternions. In Proceedings of the 2007 Symposium on Interactive 3D Graphics and Games (pp. 39\u201346).","DOI":"10.1145\/1230100.1230107"},{"issue":"4","key":"2310_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1409625.1409627","volume":"27","author":"L Kavan","year":"2008","unstructured":"Kavan, L., Collins, S., \u017d\u00e1ra, J., & O\u2019Sullivan, C. (2008). Geometric skinning with approximate dual quaternion blending. ACM Transactions on Graphics (TOG), 27(4), 1\u201323.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2310_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R. (2020). PointRend: Image segmentation as rendering. In Proceedings of the IEEE\/CVF Conference on computer Vision and Pattern Recognition (pp. 9799\u20139808).","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"2310_CR16","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., & Black, M. J. (2020). Vibe: Video inference for human body pose and shape estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 5253\u20135263).","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"2310_CR17","doi-asserted-by":"crossref","unstructured":"Kulkarni, N., Gupta, A., Fouhey, D. F., & Tulsiani, S. (2020). Articulation-aware canonical surface mapping. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 452\u2013461).","DOI":"10.1109\/CVPR42600.2020.00053"},{"key":"2310_CR18","doi-asserted-by":"crossref","unstructured":"Lewis, J. P., Cordner, M., & Fong, N. (2000). Pose space deformation: A unified approach to shape interpolation and skeleton-driven deformation. In Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques (pp. 165\u2013172).","DOI":"10.1145\/344779.344862"},{"key":"2310_CR19","doi-asserted-by":"crossref","unstructured":"Li, R., Lin, G., & Xie, L. (2021). Self-point-flow: Self-supervised scene flow estimation from point clouds with optimal transport and random walk. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 15577\u201315586).","DOI":"10.1109\/CVPR46437.2021.01532"},{"key":"2310_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, S., Kim, K., Mello, S. D., Jampani, V., Yang, M. H., & Kautz, J. (2020). Self-supervised single-view 3d reconstruction via semantic consistency. In European Conference on Computer Vision (pp. 677\u2013693).","DOI":"10.1007\/978-3-030-58568-6_40"},{"key":"2310_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Niklaus, S., Snavely, N., & Wang, O. (2021). Neural scene flow fields for space-time view synthesis of dynamic scenes. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 6498\u20136508).","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"2310_CR22","doi-asserted-by":"crossref","unstructured":"Li, R., Tanke, J., Vo, M., Zollh\u00f6fer, M., Gall, J., Kanazawa, A., & Lassner, C. (2022). TAVA: Template-free animatable volumetric actors. In European Conference on Computer Vision (pp. 419\u2013436).","DOI":"10.1007\/978-3-031-19824-3_25"},{"key":"2310_CR23","first-page":"15009","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., Liu, S., De Mello, S., Kim, K., Wang, X., Yang, M. H., & Kautz, J. (2020). Online adaptation for consistent mesh reconstruction in the wild. Advances in Neural Information Processing Systems, 33, 15009\u201315019.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2310_CR24","first-page":"13485","volume":"35","author":"L Li","year":"2022","unstructured":"Li, L., Shen, Z., Shen, L., Tan, P., et al. (2022). Streaming radiance fields for 3d video synthesis. Advances in Neural Information Processing Systems, 35, 13485\u201313498.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"6","key":"2310_CR25","first-page":"1","volume":"40","author":"L Liu","year":"2021","unstructured":"Liu, L., Habermann, M., Rudnev, V., Sarkar, K., Gu, J., & Theobalt, C. (2021). Neural actor: Neural free-view synthesis of human actors with pose control. ACM Transactions on Graphics (TOG), 40(6), 1\u201316.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2310_CR26","doi-asserted-by":"publisher","first-page":"5130","DOI":"10.1109\/TMM.2022.3187855","volume":"25","author":"W Liu","year":"2022","unstructured":"Liu, W., Zhang, C., Ding, H., Hung, T. Y., & Lin, G. (2022). Few-shot segmentation with optimal transport matching and message flow. IEEE Transactions on Multimedia, 25, 5130\u20135141.","journal-title":"IEEE Transactions on Multimedia"},{"issue":"6","key":"2310_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., & Black, M. J. (2015). SMPL: A skinned multi-person linear model. ACM Transactions on Graphics (TOG), 34(6), 1\u201316.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2310_CR28","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N. F., Pons-Moll, G., & Black, M. J. (2019). AMASS: Archive of motion capture as surface shapes. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 5442\u20135451).","DOI":"10.1109\/ICCV.2019.00554"},{"issue":"1","key":"2310_CR29","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. (2021). Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1), 99\u2013106.","journal-title":"Communications of the ACM"},{"key":"2310_CR30","doi-asserted-by":"crossref","unstructured":"Neverova, N., Sanakoyeu, A., Labatut, P., Novotny, D., & Vedaldi, A. (2021). Discovering relationships between object categories via universal canonical maps. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 404\u2013413).","DOI":"10.1109\/CVPR46437.2021.00047"},{"key":"2310_CR31","first-page":"17258","volume":"33","author":"N Neverova","year":"2020","unstructured":"Neverova, N., Novotny, D., Szafraniec, M., Khalidov, V., Labatut, P., & Vedaldi, A. (2020). Continuous surface embeddings. Advances in Neural Information Processing Systems, 33, 17258\u201317270.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2310_CR32","doi-asserted-by":"crossref","unstructured":"Noguchi, A., Sun, X., Lin, S., & Harada, T. (2021). Neural articulated radiance field. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 5762\u20135772).","DOI":"10.1109\/ICCV48922.2021.00571"},{"key":"2310_CR33","doi-asserted-by":"crossref","unstructured":"Novotny, D., Larlus, D., & Vedaldi, A. (2017). Learning 3D object categories by looking around them. In Proceedings of the IEEE International Conference on Computer Vision (pp. 5218\u20135227).","DOI":"10.1109\/ICCV.2017.558"},{"key":"2310_CR34","doi-asserted-by":"crossref","unstructured":"Oechsle, M., Peng, S., & Geiger, A. (2021). Unisurf: Unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 5589\u20135599).","DOI":"10.1109\/ICCV48922.2021.00554"},{"key":"2310_CR35","doi-asserted-by":"crossref","unstructured":"Park, K., Sinha, U., Barron, J. T., Bouaziz, S., Goldman, D. B., Seitz, S. M., & Martin-Brualla, R. (2021a). Nerfies: Deformable neural radiance fields. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 5865\u20135874).","DOI":"10.1109\/ICCV48922.2021.00581"},{"issue":"6","key":"2310_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480487","volume":"40","author":"K Park","year":"2021","unstructured":"Park, K., Sinha, U., Hedman, P., Barron, J. T., Bouaziz, S., Goldman, D. B., Martin-Brualla, R., & Seitz, S. M. (2021b). HyperNeRF: A higher-dimensional representation for topologically varying neural radiance fields. ACM Transactions on Graphics (TOG), 40(6), 1\u201312.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2310_CR37","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A. A., Tzionas, D., & Black, M. J. (2019). 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).","DOI":"10.1109\/CVPR.2019.01123"},{"key":"2310_CR38","doi-asserted-by":"crossref","unstructured":"Peng, S., Dong, J., Wang, Q., Zhang, S., Shuai, Q., Zhou, X., & Bao, H. (2021). Animatable neural radiance fields for modeling dynamic human bodies. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 14314\u201314323)","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"2310_CR39","doi-asserted-by":"crossref","unstructured":"Peng, S., Zhang, Y., Xu, Y., Wang, Q., Shuai, Q., Bao, H., & Zhou, X. (2021). Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 9054\u20139063).","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"2310_CR40","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., & Moreno-Noguer, F. (2021). D-NeRF: Neural radiance fields for dynamic scenes. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 10318\u201310327)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"2310_CR41","doi-asserted-by":"crossref","unstructured":"Puy, G., Boulch, A., Marlet, R. (2020). FLOT: Scene flow on point clouds guided by optimal transport. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXVIII (pp. 527\u2013544).","DOI":"10.1007\/978-3-030-58604-1_32"},{"key":"2310_CR42","doi-asserted-by":"crossref","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., & Li, H. (2019). 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).","DOI":"10.1109\/ICCV.2019.00239"},{"key":"2310_CR43","doi-asserted-by":"crossref","unstructured":"Saito, S., Simon, T., Saragih, J., & Joo, H. (2020). 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).","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"2310_CR44","unstructured":"Shi, Y., Rong, D., Ni, B., Chen, C., & Zhang, W. (2022). GARF: Geometry-aware generalized neural radiance field. arXiv Preprint arXiv:2212.02280."},{"key":"2310_CR45","doi-asserted-by":"crossref","unstructured":"Shi, H., Wei, J., Li, R., Liu, F., & Lin, G. (2022). Weakly supervised segmentation on outdoor 4d point clouds with temporal matching and spatial graph propagation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 11840\u201311849).","DOI":"10.1109\/CVPR52688.2022.01154"},{"key":"2310_CR46","unstructured":"Shi, Y., Xiong, Y., Ni, B., & Zhang, W. (2023). USR: Unsupervised separated 3d garment and human reconstruction via geometry and semantic consistency. arXiv Preprint arXiv:2302.10518."},{"issue":"4","key":"2310_CR47","doi-asserted-by":"publisher","first-page":"402","DOI":"10.2307\/2314570","volume":"74","author":"R Sinkhorn","year":"1967","unstructured":"Sinkhorn, R. (1967). Diagonal equivalence to matrices with prescribed row and column sums. The American Mathematical Monthly, 74(4), 402\u2013405.","journal-title":"The American Mathematical Monthly"},{"key":"2310_CR48","doi-asserted-by":"crossref","unstructured":"Song, L., Chen, A., Li, Z., Chen, Z., Chen, L., Yuan, J., Xu, Y., & Geiger, A. (2022). NeRFPlayer: A streamable dynamic scene representation with decomposed neural radiance fields. arXiv Preprint arXiv:2210.15947.","DOI":"10.1109\/TVCG.2023.3247082"},{"key":"2310_CR49","first-page":"3108","volume":"34","author":"C Song","year":"2021","unstructured":"Song, C., Wei, J., Li, R., Liu, F., & Lin, G. (2021). 3D pose transfer with correspondence learning and mesh refinement. Advances in Neural Information Processing Systems, 34, 3108\u20133120.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"8","key":"2310_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2023.3259059","volume":"45","author":"C Song","year":"2023","unstructured":"Song, C., Wei, J., Li, R., Liu, F., & Lin, G. (2023). Unsupervised 3D pose transfer with cross consistency and dual reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8), 1\u201313. https:\/\/doi.org\/10.1109\/TPAMI.2023.3259059","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2310_CR51","first-page":"12278","volume":"34","author":"SY Su","year":"2021","unstructured":"Su, S. Y., Yu, F., Zollh\u00f6fer, M., & Rhodin, H. (2021). A-nerf: Articulated neural radiance fields for learning human shape, appearance, and pose. Advances in Neural Information Processing Systems, 34, 12278\u201312291.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2310_CR52","doi-asserted-by":"crossref","unstructured":"Tretschk, E., Tewari, A., Golyanik, V., Zollh\u00f6fer, M., Lassner, C., & Theobalt, C. (2021). Non-rigid neural radiance fields: Reconstruction and novel view synthesis of a dynamic scene from monocular video. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 12959\u201312970).","DOI":"10.1109\/ICCV48922.2021.01272"},{"key":"2310_CR53","doi-asserted-by":"crossref","unstructured":"Vlasic, D., Baran, I., Matusik, W., & Popovi\u0107, J. (2008). Articulated mesh animation from multi-view silhouettes. ACM SIGGRAPH papers (pp. 1\u20139).","DOI":"10.1145\/1399504.1360696"},{"issue":"2","key":"2310_CR54","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1109\/TPAMI.2020.3012429","volume":"44","author":"MP Vo","year":"2020","unstructured":"Vo, M. P., Sheikh, Y. A., & Narasimhan, S. G. (2020). Spatiotemporal bundle adjustment for dynamic 3D human reconstruction in the wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(2), 1066\u20131080.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2310_CR55","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., & Wang, W. (2021). NeuS: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv Preprint arXiv:2106.10689."},{"key":"2310_CR56","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, H., Feng, J., Lin, G., & Yap, K. H. (2023). TAPS3D: Text-guided 3d textured shape generation from pseudo supervision. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 16805\u201316815).","DOI":"10.1109\/CVPR52729.2023.01612"},{"key":"2310_CR57","doi-asserted-by":"crossref","unstructured":"Weng, C. Y., Curless, B., Srinivasan, P. P., Barron, J. T., & Kemelmacher-Shlizerman, I. (2022). HumanNerf: Free-viewpoint rendering of moving people from monocular video. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 16210\u201316220).","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"2310_CR58","unstructured":"Wu, S., Jakab, T., Rupprecht, C., Vedaldi, A. (2021). DOVE: Learning deformable 3D objects by watching videos. arXiv Preprint arXiv:2107.10844."},{"key":"2310_CR59","doi-asserted-by":"crossref","unstructured":"Wu, Q., Liu, X., Chen, Y., Li, K., Zheng, C., Cai, J., Zheng, J. (2022). Object-compositional neural implicit surfaces. In Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXVII (pp. 197\u2013213).","DOI":"10.1007\/978-3-031-19812-0_12"},{"key":"2310_CR60","doi-asserted-by":"crossref","unstructured":"Xiang, D., Joo, H., & Sheikh, Y. (2019). Monocular total capture: Posing face, body, and hands in the wild. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 10965\u201310974).","DOI":"10.1109\/CVPR.2019.01122"},{"key":"2310_CR61","doi-asserted-by":"crossref","unstructured":"Yang, F., & Lin, G. (2021). CT-Net: Complementary transfering network for garment transfer with arbitrary geometric changes. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 9899\u20139908).","DOI":"10.1109\/CVPR46437.2021.00977"},{"key":"2310_CR62","unstructured":"Yang, G., & Ramanan, D. (2019). Volumetric correspondence networks for optical flow. Advances in Neural Information Processing Systems32"},{"key":"2310_CR63","doi-asserted-by":"crossref","unstructured":"Yang, F., Chen, T., He, X., Cai, Z., Yang, L., Wu, S., & Lin, G. (2023). Attrihuman-3D: Editable 3D human avatar generation with attribute decomposition and indexing. arXiv Preprint arXiv:2312.02209.","DOI":"10.1109\/CVPR52733.2024.01008"},{"key":"2310_CR64","doi-asserted-by":"crossref","unstructured":"Yang, G., Sun, D., Jampani, V., Vlasic, D., Cole, F., Chang, H., Ramanan, D., Freeman, & Liu, C. (2021). LASR: Learning articulated shape reconstruction from a monocular video. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 15980\u201315989).","DOI":"10.1109\/CVPR46437.2021.01572"},{"key":"2310_CR65","doi-asserted-by":"crossref","unstructured":"Yang, G., Vo, M., Neverova, N., Ramanan, D., Vedaldi, A., & Joo, H. (2022). BANMo: Building animatable 3d neural models from many casual videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 2863\u20132873).","DOI":"10.1109\/CVPR52688.2022.00288"},{"key":"2310_CR66","doi-asserted-by":"crossref","unstructured":"Yang, G., Wang, C., Reddy, N. D., & Ramanan, D. (2023). Reconstructing animatable categories from videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 16995\u201317005).","DOI":"10.1109\/CVPR52729.2023.01630"},{"key":"2310_CR67","first-page":"19326","volume":"34","author":"G Yang","year":"2021","unstructured":"Yang, G., Sun, D., Jampani, V., Vlasic, D., Cole, F., Liu, C., & Ramanan, D. (2021). Viser: Video-specific surface embeddings for articulated 3d shape reconstruction. Advances in Neural Information Processing Systems, 34, 19326\u201319338.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2310_CR68","first-page":"4805","volume":"34","author":"L Yariv","year":"2021","unstructured":"Yariv, L., Gu, J., Kasten, Y., & Lipman, Y. (2021). Volume rendering of neural implicit surfaces. Advances in Neural Information Processing Systems, 34, 4805\u20134815.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2310_CR69","first-page":"2492","volume":"33","author":"L Yariv","year":"2020","unstructured":"Yariv, L., Kasten, Y., Moran, D., Galun, M., Atzmon, M., Ronen, B., & Lipman, Y. (2020). Multiview neural surface reconstruction by disentangling geometry and appearance. Advances in Neural Information Processing Systems, 33, 2492\u20132502.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2310_CR70","doi-asserted-by":"crossref","unstructured":"Ye, Y., Tulsiani, S., Gupta, A. (2021). Shelf-supervised mesh prediction in the wild. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 8843\u20138852).","DOI":"10.1109\/CVPR46437.2021.00873"},{"key":"2310_CR71","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., & Kanazawa, A. (2021). pixelNeRF: Neural radiance fields from one or few images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 4578\u20134587).","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"2310_CR72","first-page":"29835","volume":"34","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Yang, G., Tulsiani, S., & Ramanan, D. (2021). NERS: Neural reflectance surfaces for sparse-view 3d reconstruction in the wild. Advances in Neural Information Processing Systems, 34, 29835\u201329847.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2310_CR73","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., & Davison, A. J. (2021). In-place scene labelling and understanding with implicit scene representation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 15838\u201315847).","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"2310_CR74","doi-asserted-by":"crossref","unstructured":"Zuffi, S., Kanazawa, A., & Black, M. J. (2018). Lions and tigers and bears: Capturing non-rigid, 3d, articulated shape from images. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (pp. 3955\u20133963).","DOI":"10.1109\/CVPR.2018.00416"},{"key":"2310_CR75","doi-asserted-by":"crossref","unstructured":"Zuffi, S., Kanazawa, A., Berger-Wolf, T., & Black, M. J. (2019). Three-d safari: Learning to estimate zebra pose, shape, and texture from images\u201c in the wild\u201d. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 5359\u20135368).","DOI":"10.1109\/ICCV.2019.00546"},{"key":"2310_CR76","doi-asserted-by":"crossref","unstructured":"Zuffi, S., Kanazawa, A., Jacobs, D. W., & Black, M. J. (2017). 3D menagerie: Modeling the 3D shape and pose of animals. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 6365\u20136373).","DOI":"10.1109\/CVPR.2017.586"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02310-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02310-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02310-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T06:04:29Z","timestamp":1744869869000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02310-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,12]]},"references-count":76,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2310"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02310-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,12]]},"assertion":[{"value":"12 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Author Chaoyue Song has received research support from A*STAR. Author Fayao Liu and Chuan-Sheng Foo receive salaries from A*STAR. Author Guosheng Lin receives a salary from Nanyang Technological University.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Yes.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Yes.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}]}}