{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:25:15Z","timestamp":1777656315944,"version":"3.51.4"},"publisher-location":"Cham","reference-count":94,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730061","type":"print"},{"value":"9783031730078","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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\/978-3-031-73007-8_15","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T19:02:40Z","timestamp":1727722960000},"page":"246-264","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DiffSurf: A Transformer-Based Diffusion Model for\u00a0Generating and\u00a0Reconstructing 3D Surfaces in\u00a0Pose"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0433-9832","authenticated-orcid":false,"given":"Yusuke","family":"Yoshiyasu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6123-9339","authenticated-orcid":false,"given":"Leyuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"15_CR1","unstructured":"Alliegro, A., Siddiqui, Y., Tommasi, T., Nie\u00dfner, M.: PolyDiff: generating 3D polygonal meshes with diffusion models (2023)"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Bernt, S.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Aumentado-Armstrong, T., Tsogkas, S., Jepson, A., Dickinson, S.: Geometric disentanglement for generative latent shape models. In: ICCV, pp. 8180\u20138189 (2019)","DOI":"10.1109\/ICCV.2019.00827"},{"key":"15_CR4","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":"15_CR5","unstructured":"Bao, F., et al.: One transformer fits all distributions in multi-modal diffusion at scale (2023)"},{"key":"15_CR6","unstructured":"Bautista, M.A., et al.: GAUDI: a neural architect for immersive 3D scene generation. arXiv (2022)"},{"key":"15_CR7","unstructured":"Biggs, B., Ehrhart, S., Joo, H., Graham, B., Vedaldi, A., Novotny, D.: 3D multibodies: fitting sets of plausible 3D models to ambiguous image data. In: NeurIPS (2020)"},{"key":"15_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Bogo, F., Romero, J., Pons-Moll, G., Black, M.J.: Dynamic FAUST: registering human bodies in motion. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.591"},{"key":"15_CR10","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository (2015)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Chen, H., Tang, H., Shi, H., Peng, W., Sebe, N., Zhao, G.: Intrinsic-extrinsic preserved GANs for unsupervised 3D pose transfer. In: ICCV, pp. 8610\u20138619 (2021)","DOI":"10.1109\/ICCV48922.2021.00851"},{"key":"15_CR12","unstructured":"Cheng, S., Bronstein, M.M., Zhou, Y., Kotsia, I., Pantic, M., Zafeiriou, S.: MeshGAN: non-linear 3D morphable models of faces. CoRR abs\/1903.10384 (2019)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, Y.C., Lee, H.Y., Tulyakov, S., Schwing, A.G., Gui, L.Y.: SDFusion: multimodal 3D shape completion, reconstruction, and generation. In: CVPR, pp. 4456\u20134465 (2023)","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Cho, H., Kim, J.: Generative approach for probabilistic human mesh recovery using diffusion models (2023)","DOI":"10.1109\/ICCVW60793.2023.00452"},{"key":"15_CR15","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/978-3-031-19769-7_20","volume-title":"ECCV 2022","author":"J Cho","year":"2022","unstructured":"Cho, J., Youwang, K., Oh, T.H.: Cross-attention of disentangled modalities for 3D human mesh recovery with transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13661, pp. 342\u2013359. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_20"},{"key":"15_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1007\/978-3-030-58571-6_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Choi","year":"2020","unstructured":"Choi, H., Moon, G., Lee, K.M.: Pose2Mesh: graph convolutional network for 3D human pose and mesh recovery from a 2D human pose. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 769\u2013787. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_45"},{"key":"15_CR17","unstructured":"Christian, Z., Duygu, C., Jimei, Y., Russel, B., Argus, M., Brox, T.: FreiHAND: a dataset for markerless capture of hand pose and shape from single RGB images. In: ICCV (2019)"},{"key":"15_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/978-3-030-58580-8_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Cosmo","year":"2020","unstructured":"Cosmo, L., Norelli, A., Halimi, O., Kimmel, R., Rodol\u00e0, E.: LIMP: learning latent shape representations with metric preservation\u00a0priors. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 19\u201335. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_2"},{"key":"15_CR19","unstructured":"Dao, T., Fu, D.Y., Ermon, S., Rudra, A., R\u00e9, C.: FlashAttention: fast and memory-efficient exact attention with IO-awareness. In: NeurIPS (2022)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Davydov, A., Remizova, A., Constantin, V., Honari, S., Salzmann, M., Fua, P.: Adversarial parametric pose prior. In: CVPR, pp. 10987\u201310995 (2022)","DOI":"10.1109\/CVPR52688.2022.01072"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Desbrun, M., Meyer, M., Schr\u00f6der, P., Barr, A.H.: Implicit fairing of irregular meshes using diffusion and curvature flow. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999, pp. 317\u2013324 (1999)","DOI":"10.1145\/311535.311576"},{"issue":"8","key":"15_CR22","doi-asserted-by":"publisher","first-page":"2246","DOI":"10.1111\/j.1467-8659.2011.01974.x","volume":"30","author":"S Fr\u00f6hlich","year":"2011","unstructured":"Fr\u00f6hlich, S., Botsch, M.: Example-driven deformations based on discrete shells. Comput. Graph. Forum 30(8), 2246\u20132257 (2011)","journal-title":"Comput. Graph. Forum"},{"issue":"3","key":"15_CR23","doi-asserted-by":"publisher","first-page":"2085","DOI":"10.1109\/TVCG.2019.2941200","volume":"27","author":"L Gao","year":"2021","unstructured":"Gao, L., Lai, Y.K., Yang, J., Zhang, L.X., Xia, S., Kobbelt, L.: Sparse data driven mesh deformation. IEEE Trans. Vis. Comput. Graph. 27(3), 2085\u20132100 (2021)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"15_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/978-3-030-58520-4_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Georgakis","year":"2020","unstructured":"Georgakis, G., Li, R., Karanam, S., Chen, T., Ko\u0161eck\u00e1, J., Wu, Z.: Hierarchical kinematic human mesh recovery. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 768\u2013784. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_45"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Gong, J., Foo, L.G., Fan, Z., Ke, Q., Rahmani, H., Liu, J.: DiffPose: toward more reliable 3D pose estimation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01253"},{"key":"15_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-030-01216-8_15","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Groueix","year":"2018","unstructured":"Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: 3D-CODED: 3D correspondences by deep deformation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 235\u2013251. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_15"},{"key":"15_CR27","unstructured":"Ho, J.: Classifier-free diffusion guidance. arXiv abs\/2207.12598 (2022)"},{"key":"15_CR28","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. arXiv preprint arxiv:2006.11239 (2020)"},{"issue":"7","key":"15_CR29","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE TPAMI 36(7), 1325\u20131339 (2014)","journal-title":"IEEE TPAMI"},{"issue":"8","key":"15_CR30","doi-asserted-by":"publisher","first-page":"2560","DOI":"10.1109\/TVCG.2020.2988476","volume":"26","author":"B Jiang","year":"2020","unstructured":"Jiang, B., Zhang, J., Cai, J., Zheng, J.: Disentangled human body embedding based on deep hierarchical neural network. IEEE Trans. Vis. Comput. Graph. 26(8), 2560\u20132575 (2020)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: CVPR, pp. 1465\u20131472 (2011)","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3D human pose fitting towards in-the-wild 3D human pose estimation. In: 3DV (2020)","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"15_CR33","unstructured":"Jun, H., Nichol, A.: Shap-E: generating conditional 3D implicit functions (2023)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Tripathi, S., Kitani, K.: Occluded human mesh recovery. In: CVPR, pp. 1715\u20131725 (2022)","DOI":"10.1109\/CVPR52688.2022.00176"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: PARE: part attention regressor for 3D human body estimation. In: ICCV, pp. 11127\u201311137 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00463"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Jayaraman, D., Daniilidis, K.: Probabilistic modeling for human mesh recovery. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01140"},{"key":"15_CR40","unstructured":"Li, L., Zhuo, L., Zhang, B., Bo, L., Chen, C.: DiffHand: end-to-end hand mesh reconstruction via diffusion models (2023)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"15_CR42","unstructured":"Lin, G.F., Jia, G., Hossein, R., Jun, L.: Distribution-aligned diffusion for human mesh recovery. In: ICCV (2023)"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: Mesh graphormer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Lin, T., et al.: Microsoft COCO: common objects in context. CoRR abs\/1405.0312 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yang, J., Gu, X., Guo, Y., Yang, G.Z.: EgoHMR: egocentric human mesh recovery via hierarchical latent diffusion model. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 9807\u20139813 (2023)","DOI":"10.1109\/ICRA48891.2023.10161247"},{"key":"15_CR47","unstructured":"Liu, Z., Feng, Y., Black, M.J., Nowrouzezahrai, D., Paull, L., Liu, W.: MeshDiffusion: score-based generative 3D mesh modeling. In: International Conference on Learning Representations (2023)"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM TOG 34(6), 248:1\u2013248:16 (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Luo, S., Hu, W.: Diffusion probabilistic models for 3D point cloud generation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"15_CR50","unstructured":"Lyu, Z., Kong, Z., Xu, X., Pan, L., Lin, D.: A conditional point diffusion-refinement paradigm for 3D point cloud completion (2022)"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Lyu, Z., Wang, J., An, Y., Zhang, Y., Lin, D., Dai, B.: Controllable mesh generation through sparse latent point diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00034"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Ma, Q., et al.: Learning to dress 3D people in generative clothing. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00650"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"15_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1007\/978-3-030-01249-6_37","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T von Marcard","year":"2018","unstructured":"von Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 614\u2013631. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_37"},{"key":"15_CR55","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 3DV. IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"15_CR56","unstructured":"Mo, S., Xie, E., Chu, R., Hong, L., Nie\u00dfner, M., Li, Z.: DiT-3D: exploring plain diffusion transformers for 3D shape generation. arXiv preprint arXiv: 2307.01831 (2023)"},{"key":"15_CR57","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-E: a system for generating 3D point clouds from complex prompts (2022)"},{"key":"15_CR58","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"15_CR59","unstructured":"Peebles, W., Radosavovic, I., Brooks, T., Efros, A., Malik, J.: Learning to learn with generative models of neural network checkpoints. arXiv preprint arXiv:2209.12892 (2022)"},{"key":"15_CR60","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. arXiv preprint arXiv:2212.09748 (2022)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"15_CR61","unstructured":"Peng, S., Jiang, C.M., Liao, Y., Niemeyer, M., Pollefeys, M., Geiger, A.: Shape as points: a differentiable Poisson solver. In: NeurIPS (2021)"},{"key":"15_CR62","unstructured":"Phil, W.: denoising-diffusion-pytorch (2023). https:\/\/github.com\/lucidrains\/denoising-diffusion-pytorch"},{"key":"15_CR63","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. arXiv (2022)"},{"key":"15_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1007\/978-3-030-01219-9_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Ranjan","year":"2018","unstructured":"Ranjan, A., Bolkart, T., Sanyal, S., Black, M.J.: Generating 3D faces using convolutional mesh autoencoders. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 725\u2013741. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_43"},{"key":"15_CR65","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"},{"issue":"6","key":"15_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3130800.3130883","volume":"36","author":"J Romero","year":"2017","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM TOG 36(6), 1\u201317 (2017)","journal-title":"ACM TOG"},{"key":"15_CR67","doi-asserted-by":"crossref","unstructured":"Rueegg, N., Zuffi, S., Schindler, K., Black, M.J.: BARC: learning to regress 3D dog shape from images by exploiting breed information. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00385"},{"key":"15_CR68","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models (2022)"},{"key":"15_CR69","doi-asserted-by":"crossref","unstructured":"Shan, W., et al.: Diffusion-based 3D human pose estimation with multi-hypothesis aggregation. arXiv preprint arXiv:2303.11579 (2023)","DOI":"10.1109\/ICCV51070.2023.01356"},{"key":"15_CR70","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"15_CR71","doi-asserted-by":"crossref","unstructured":"Shim, J., Kang, C., Joo, K.: Diffusion-based signed distance fields for 3D shape generation. In: CVPR, pp. 20887\u201320897 (2023)","DOI":"10.1109\/CVPR52729.2023.02001"},{"key":"15_CR72","doi-asserted-by":"crossref","unstructured":"Shoemake, K.: Animating rotation with quaternion curves. In: Proceedings of the 12th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1985, pp. 245\u2013254. Association for Computing Machinery, New York (1985)","DOI":"10.1145\/325334.325242"},{"key":"15_CR73","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv:2010.02502 (2020)"},{"key":"15_CR74","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-030-58565-5_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Song","year":"2020","unstructured":"Song, J., Chen, X., Hilliges, O.: Human body model fitting by learned gradient descent. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 744\u2013760. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_44"},{"issue":"3","key":"15_CR75","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1145\/1073204.1073218","volume":"24","author":"RW Sumner","year":"2005","unstructured":"Sumner, R.W., Zwicker, M., Gotsman, C., Popovic, J.: Mesh-based inverse kinematics. ACM TOG 24(3), 488\u2013495 (2005)","journal-title":"ACM TOG"},{"key":"15_CR76","doi-asserted-by":"crossref","unstructured":"Sun, X., et al.: Learning semantic-aware disentangled representation for flexible 3D human body editing. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01629"},{"key":"15_CR77","doi-asserted-by":"crossref","unstructured":"Tan, Q., Gao, L., Lai, Y.K., Xia, S.: Variational autoencoders for deforming 3D mesh models. In: CVPR, pp. 5841\u20135850 (2018)","DOI":"10.1109\/CVPR.2018.00612"},{"key":"15_CR78","doi-asserted-by":"crossref","unstructured":"Tian, Y., Zhang, H., Liu, Y., Wang, L.: Recovering 3D human mesh from monocular images: a survey. arXiv preprint arXiv:2203.01923 (2022)","DOI":"10.1109\/TPAMI.2023.3298850"},{"key":"15_CR79","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/978-3-031-20065-6_33","volume-title":"ECCV 2022","author":"G Tiwari","year":"2022","unstructured":"Tiwari, G., Anti\u0107, D., Lenssen, J.E., Sarafianos, N., Tung, T., Pons-Moll, G.: Pose-NDF: modeling human pose manifolds with neural distance fields. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13665, pp. 572\u2013589. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_33"},{"key":"15_CR80","doi-asserted-by":"crossref","unstructured":"Varol, G., et al.: Learning from synthetic humans. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.492"},{"key":"15_CR81","unstructured":"Wang, Z., et al.: ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. arXiv preprint arXiv:2305.16213 (2023)"},{"key":"15_CR82","doi-asserted-by":"crossref","unstructured":"Xu, H., Bazavan, E.G., Zanfir, A., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: GHUM & GHUML: generative 3D human shape and articulated pose models. In: CVPR, pp. 6184\u20136193 (2020)","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"15_CR83","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Animal3D: a comprehensive dataset of 3D animal pose and shape. arXiv preprint arXiv:2308.11737 (2023)","DOI":"10.1109\/ICCV51070.2023.00835"},{"key":"15_CR84","doi-asserted-by":"crossref","unstructured":"Xu, X., Wang, Z., Zhang, G., Wang, K., Shi, H.: Versatile diffusion: text, images and variations all in one diffusion model. In: ICCV, pp. 7754\u20137765 (2023)","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"15_CR85","doi-asserted-by":"crossref","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: PointFlow: 3D point cloud generation with continuous normalizing flows. arXiv (2019)","DOI":"10.1109\/ICCV.2019.00464"},{"key":"15_CR86","doi-asserted-by":"crossref","unstructured":"Yoshiyasu, Y.: Deformable mesh transformer for 3D human mesh recovery. In: CVPR, pp. 17006\u201317015 (2023)","DOI":"10.1109\/CVPR52729.2023.01631"},{"key":"15_CR87","doi-asserted-by":"crossref","unstructured":"You, Y., Liu, H., Li, X., Li, W., Wang, T., Ding, R.: GATOR: graph-aware transformer with motion-disentangled regression for human mesh recovery from a 2D pose. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096870"},{"key":"15_CR88","unstructured":"Yu, Z., et al.: Surf-D: high-quality surface generation for arbitrary topologies using diffusion models. arXiv preprint arXiv:2311.17050 (2023)"},{"key":"15_CR89","doi-asserted-by":"crossref","unstructured":"Yuan, Y.J., Lai, Y.K., Yang, J., Duan, Q., Fu, H., Gao, L.: Mesh variational autoencoders with edge contraction pooling. In: CVPRW, pp. 274\u2013275 (2020)","DOI":"10.1109\/CVPRW50498.2020.00145"},{"key":"15_CR90","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/978-3-030-58539-6_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Zanfir","year":"2020","unstructured":"Zanfir, A., Bazavan, E.G., Xu, H., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Weakly supervised 3D human pose and shape reconstruction with normalizing flows. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 465\u2013481. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_28"},{"key":"15_CR91","unstructured":"Zeng, X., et al.: LION: latent point diffusion models for 3D shape generation. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"15_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: PyMAF: 3D human pose and shape regression with pyramidal mesh alignment feedback loop. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01125"},{"key":"15_CR93","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/978-3-030-58542-6_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Zhou","year":"2020","unstructured":"Zhou, K., Bhatnagar, B.L., Pons-Moll, G.: Unsupervised shape and pose disentanglement for 3D meshes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 341\u2013357. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_21"},{"key":"15_CR94","doi-asserted-by":"crossref","unstructured":"Zuffi, S., Kanazawa, A., Jacobs, D., Black, M.J.: 3D menagerie: modeling the 3D shape and pose of animals. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.586"}],"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\/978-3-031-73007-8_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T19:09:09Z","timestamp":1727723349000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73007-8_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031730061","9783031730078"],"references-count":94,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73007-8_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 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"}}]}}