Abstract
Reconstructing 3D human shapes with high-quality geometry as well as dense correspondences is important for many applications. Template fitting based methods can generate meshes with desired requirements but have difficulty in capturing high-quality details and accurate poses. The main challenge lies in the models have apparent discrepancies in different poses. Directly learning large-scale displacement of each point to account for different posed shapes is prone to artifacts and does not generalize well. Statistic representation based methods, can avoid artifacts by restricting human shapes to a limited shape expression space, which also makes it difficult to produce shape details. In this work, we propose a coarse-to-fine method to address the problem by dividing it into part approximation and shape refinement in an unsupervised manner. Our basic observation is that the poses of human parts account for most articulated shape variations and benefit pose generalization. Moreover, geometry details can be easily fitted once the part poses are estimated. At the coarse-fitting stage, we propose a part approximation network, to transform a template to fit inputs by a set of pose parameters. For refinement, we propose a shape refinement network, to fit shape details. Qualitative and quantitative studies on several datasets demonstrate that our method performs better than other unsupervised methods.
This work is supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (No. XDA23090304), the National Natural Science Foundation of China (U2003109, U21A20515, 62102393), the Youth Innovation Promotion Association of the Chinese Academy of Sciences (Y201935), the State Key Laboratory of Robotics and Systems (HIT) (SKLRS-2022-KF-11), and the Fundamental Research Funds for the Central Universities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amberg, B., Romdhani, S., Vetter, T.: Optimal step nonrigid ICP algorithms for surface registration. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 1–8. IEEE (2007)
Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Scape: shape completion and animation of people. In: ACM SIGGRAPH 2005 Papers, SIGGRAPH 2005, pp. 408–416. Association for Computing Machinery, New York (2005)
Atzmon, M., Lipman, Y.: SAL: sign agnostic learning of shapes from raw data. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 2565–2574 (2020)
Aubry, M., Schlickewei, U., Cremers, D.: The wave kernel signature: a quantum mechanical approach to shape analysis. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1626–1633. IEEE (2011)
Bhatnagar, B.L., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Loopreg: self-supervised learning of implicit surface correspondences, pose and shape for 3D human mesh registration. In: NeurIPS, vol. 33 (2020)
Bogo, F., Romero, J., Pons-Moll, G., Black, M.J.: Dynamic FAUST: registering human bodies in motion. In: IEEE Computer Vision and Pattern Recognition (CVPR) (2017)
Chen, R., Cong, Y., Dong, J.: Unsupervised dense deformation embedding network for template-free shape correspondence. In: IEEE International Conference on Computer Vision (ICCV), pp. 8361–8370 (2021)
Chen, Z., Zhang, H.: Learning implicit fields for generative shape modeling. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 5939–5948 (2019)
Eisenberger, M., Lahner, Z., Cremers, D.: Smooth shells: multi-scale shape registration with functional maps. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 12265–12274 (2020)
Feng, W., Zhang, J., Cai, H., Xu, H., Hou, J., Bao, H.: Recurrent multi-view alignment network for unsupervised surface registration. In: IEEE Computer Vision and Pattern Recognition (CVPR) (2021)
Gilani, S.Z., Mian, A., Shafait, F., Reid, I.: Dense 3D face correspondence. IEEE Trans. Pattern Anal. Mach. Intell. 40(7), 1584–1598 (2017)
Ginzburg, D., Raviv, D.: Cyclic functional mapping: self-supervised correspondence between non-isometric deformable shapes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 36–52. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_3
Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: 3D-coded: 3D correspondences by deep deformation. In: European Conference on Computer Vision (ECCV), pp. 230–246 (2018)
Hasler, N., Stoll, C., Sunkel, M., Rosenhahn, B., Seidel, H.P.: A statistical model of human pose and body shape. In: Computer Graphics Forum, vol. 28, pp. 337–346. Wiley Online Library (2009)
Jiang, H., Cai, J., Zheng, J.: Skeleton-aware 3D human shape reconstruction from point clouds. In: IEEE International Conference on Computer Vision (ICCV), pp. 5431–5441 (2019)
Kim, H., Kim, J., Kam, J., Park, J., Lee, S.: Deep virtual markers for articulated 3D shapes. In: IEEE International Conference on Computer Vision (ICCV), pp. 11615–11625 (2021)
Li, C.L., Simon, T., Saragih, J., Póczos, B., Sheikh, Y.: LBS autoencoder: self-supervised fitting of articulated meshes to point clouds. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 11967–11976 (2019)
Liu, Z., Huang, J., Bu, S., Han, J., Tang, X., Li, X.: Template deformation-based 3-D reconstruction of full human body scans from low-cost depth cameras. IEEE Trans. Cybern. 47(3), 695–708 (2016)
Ma, Q., et al.: Learning to dress 3D people in generative clothing. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 6469–6478 (2020)
Marin, R., Melzi, S., Rodola, E., Castellani, U.: Farm: functional automatic registration method for 3D human bodies. In: Computer Graphics Forum, vol. 39, pp. 160–173. Wiley Online Library (2020)
Pan, X., et al.: Predicting loose-fitting garment deformations using bone-driven motion networks. ACM Trans. Graph. (2022)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 652–660 (2017)
Rakotosaona, M.-J., Ovsjanikov, M.: Intrinsic point cloud interpolation via dual latent space navigation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 655–672. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_39
Saito, S., Yang, J., Ma, Q., Black, M.J.: Scanimate: weakly supervised learning of skinned clothed avatar networks. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 2886–2897 (2021)
Sharma, A., Ovsjanikov, M.: Weakly supervised deep functional map for shape matching. In: NeurIPS (2020)
Sun, J., Ovsjanikov, M., Guibas, L.J.: A concise and provably informative multi-scale signature based on heat diffusion. Comput. Graph. Forum 28(5), 1383–1392 (2009)
Tang, J., Xu, D., Jia, K., Zhang, L.: Learning parallel dense correspondence from spatio-temporal descriptors for efficient and robust 4D reconstruction. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 6022–6031 (2021)
Wang, K., Xie, J., Zhang, G., Liu, L., Yang, J.: Sequential 3D human pose and shape estimation from point clouds. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 7275–7284 (2020)
Wang, S., Geiger, A., Tang, S.: Locally aware piecewise transformation fields for 3D human mesh registration. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 7639–7648 (2021)
Wei, L., Huang, Q., Ceylan, D., Vouga, E., Li, H.: Dense human body correspondences using convolutional networks. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 1544–1553 (2016)
Yang, K., Chen, X.: Unsupervised learning for cuboid shape abstraction via joint segmentation from point clouds. ACM Trans. Graph. (2021)
Yifan, W., Aigerman, N., Kim, V.G., Chaudhuri, S., Sorkine-Hornung, O.: Neural cages for detail-preserving 3D deformations. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 75–83 (2020)
Zeng, Y., Qian, Y., Zhu, Z., Hou, J., Yuan, H., He, Y.: CorrNet3D: unsupervised end-to-end learning of dense correspondence for 3D point clouds. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 6052–6061 (2021)
Zheng, Z., Yu, T., Wei, Y., Dai, Q., Liu, Y.: Deephuman: 3D human reconstruction from a single image. In: IEEE International Conference on Computer Vision (ICCV), pp. 7739–7749 (2019)
Zuffi, S., Kanazawa, A., Jacobs, D.W., Black, M.J.: 3D menagerie: modeling the 3D shape and pose of animals. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 6365–6373 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Diao, J., Jiang, H., Yan, F., Zhang, Y., Luan, J., Xiao, J. (2024). Unsupervised 3D Articulated Object Correspondences with Part Approximation and Shape Refinement. In: Hu, SM., Cai, Y., Rosin, P. (eds) Computer-Aided Design and Computer Graphics. CADGraphics 2023. Lecture Notes in Computer Science, vol 14250. Springer, Singapore. https://doi.org/10.1007/978-981-99-9666-7_1
Download citation
DOI: https://doi.org/10.1007/978-981-99-9666-7_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-9665-0
Online ISBN: 978-981-99-9666-7
eBook Packages: Computer ScienceComputer Science (R0)