skip to main content
research-article

Efficient Deformation Learning of Varied Garments with a Structure-Preserving Multilevel Framework

Published: 13 May 2024 Publication History

Abstract

Due to the highly nonlinear behavior of clothing, modelling fine-scale garment deformation on arbitrary meshes under varied conditions within a unified network poses a significant challenge. Existing methods often compromise on either model generalization, deformation quality, or runtime speed, making them less suitable for real-world applications. To address it, we propose to incorporate multi-source graph construction and pooling to achieve a novel graph learning scheme. We first introduce methods for extracting cues from different deformation correlations and transform the garment mesh into a comprehensive graph enriched with deformation-related information. To enhance the learning capability and generalizability of the model, we present structure-preserving pooling and unpooling strategies for the mesh deformation task, thereby improving information propagation across the mesh and enhancing the realism of deformation. Lastly, we conduct an attribution analysis and visualize the contribution of various vertices in the graph to the output, providing insights into the deformation behavior. The experimental results demonstrate superior performance against state-of-the-art methods.

Supplemental Material

MP4 File
Supplemental video
PDF File
Network architecture, loss functions, dataset generation, network training, replication details

References

[1]
Hugo Bertiche, Meysam Madadi, and Sergio Escalera. 2020. CLOTH3D: clothed 3d humans. In Proc. Eur. Conf. Comput. Vis. 344--359.
[2]
Hugo Bertiche, Meysam Madadi, and Sergio Escalera. 2021. PBNS: Physically Based Neural Simulation for Unsupervised Garment Pose Space Deformation. ACM Trans. Graph. 40, 6, Article 198 (2021). https://doi.org/10.1145/3478513.3480479
[3]
Hugo Bertiche, Meysam Madadi, and Sergio Escalera. 2022. Neural Cloth Simulation. ACM Trans. Graph. 41, 6, Article 220 (2022). https://doi.org/10.1145/3550454.3555491
[4]
Carnegie-Mellon. 2010. CMU graphics lab motion capture database. http://mocap.cs.cmu.edu/. Accessed: 2023.
[5]
Zhen Chen, Hsiao-Yu Chen, Danny M. Kaufman, Mélina Skouras, and Etienne Vouga. 2021. Fine Wrinkling on Coarsely Meshed Thin Shells. ACM Trans. Graph. 40, 5, Article 190 (2021). https://doi.org/10.1145/3462758
[6]
Kwang-Jin Choi and Hyeong-Seok Ko. 2002. Stable but Responsive Cloth. ACM Trans. Graph. 21, 3 (jul 2002), 604--611. https://doi.org/10.1145/566654.566624
[7]
Gabriel Cirio, Jorge Lopez-Moreno, David Miraut, and Miguel A. Otaduy. 2014a. Yarn-Level Simulation of Woven Cloth. ACM Trans. Graph. 33, 6, Article 207 (2014). https://doi.org/10.1145/2661229.2661279
[8]
Gabriel Cirio, Jorge Lopez-Moreno, David Miraut, and Miguel A. Otaduy. 2014b. Yarn-Level Simulation of Woven Cloth. ACM Trans. Graph. 33, 6, Article 207 (2014). https://doi.org/10.1145/2661229.2661279
[9]
Charless Fowlkes, Serge Belongie, Fan Chung, and Jitendra Malik. 2004. Spectral grouping using the Nystrom method. IEEE Trans. Pattern Anal. Mach. Intell. 26, 2 (2004), 214--225. https://doi.org/10.1109/TPAMI.2004.1262185
[10]
Hongyang Gao and Shuiwang Ji. 2022. Graph U-Nets. IEEE Trans. Pattern Anal. Mach. Intell. 44, 9 (2022), 4948--4960. https://doi.org/10.1109/TPAMI.2021.3081010
[11]
Artur Grigorev, Bernhard Thomaszewski, Michael J Black, and Otmar Hilliges. 2023. HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 16965--16974. https://doi.org/10.1109/CVPR52729.2023.01627
[12]
Erhan Gundogdu, Victor Constantin, Shaifali Parashar, Amrollah Seifoddini, Minh Dang, Mathieu Salzmann, and Pascal Fua. 2022. GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1 (2022), 181--195. https://doi.org/10.1109/TPAMI.2020.3010886
[13]
Fabian Hahn, Bernhard Thomaszewski, Stelian Coros, Robert W. Sumner, Forrester Cole, Mark Meyer, Tony DeRose, and Markus Gross. 2014. Subspace Clothing Simulation Using Adaptive Bases. ACM Trans. Graph. 33, 4, Article 105 (2014). https://doi.org/10.1145/2601097.2601160
[14]
Moon-Hwan Jeong, Dong-Hoon Han, and Hyeong-Seok Ko. 2015. Garment capture from a photograph. Comput. Animat. Virtual Worlds 26 (2015), 291--300. https://doi.org/10.1002/cav.1653
[15]
Chenfanfu Jiang, Theodore Gast, and Joseph Teran. 2017. Anisotropic Elastoplasticity for Cloth, Knit and Hair Frictional Contact. ACM Trans. Graph. 36, 4, Article 152 (2017). https://doi.org/10.1145/3072959.3073623
[16]
Junhyun Lee, Inyeop Lee, and Jaewoo Kang. 2019. Self-Attention Graph Pooling. In Proc. Int. Conf. Mach. Learn., Vol. 97. 3734--3743.
[17]
John P. Lewis, Cordner Matt, and Fong. Nickson. 2000. Pose Space Deformation: A Unified Approach to Shape Interpolation and Skeleton-Driven Deformation. In Proc. Annu. Conf. Comput. Graph. Interact. Tech. 165--172. https://doi.org/10.1145/344779.344862
[18]
Jie Li, Gilles Daviet, Rahul Narain, Florence Bertails-Descoubes, Matthew Overby, George E. Brown, and Laurence Boissieux. 2018. An Implicit Frictional Contact Solver for Adaptive Cloth Simulation. ACM Trans. Graph. 37, 4, Article 52 (2018). https://doi.org/10.1145/3197517.3201308
[19]
Tianxing Li, Rui Shi, and Takashi Kanai. 2020. DenseGATs: A Graph-Attention-Based Network for Nonlinear Character Deformation. In Proc. Symp. Interactive 3D Graph. Games. 5:1--5:9. https://doi.org/10.1145/3384382.3384525
[20]
Tianxing Li, Rui Shi, and Takashi Kanai. 2021. MultiResGNet: Approximating Nonlinear Deformation via Multi-Resolution Graphs. Comput. Graph. Forum 40, 2 (2021), 537--548. https://doi.org/10.1111/cgf.142653
[21]
Tianxing Li, Rui Shi, and Takashi Kanai. 2023a. Detail-Aware Deep Clothing Animations Infused with Multi-Source Attributes. Comput. Graph. Forum 42, 1 (2023), 231--244. https://doi.org/10.1111/cgf.14651
[22]
Tianxing Li, Rui Shi, Qing Zhu, and Takashi Kanai. 2023b. SwinGar: Spectrum-Inspired Neural Dynamic Deformation for Free-Swinging Garments. IEEE Trans. Vis. Comput. Graphics (2023), 1--16. https://doi.org/10.1109/TVCG.2023.3346055
[23]
Mario Lino, Chris D. Cantwell, Anil A. Bharath, and Stathi Fotiadis. 2021. Simulating Continuum Mechanics with Multi-Scale Graph Neural Networks. arXiv:2106.04900 (2021).
[24]
Mario Lino, Stathi Fotiadis, Anil A. Bharath, and Chris D. Cantwell. 2022. Multi-scale rotation-equivariant graph neural networks for unsteady Eulerian fluid dynamics. Phys. Fluids 34, 8 (08 2022), 087110. https://doi.org/10.1063/5.0097679
[25]
Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, and Michael J. Black. 2015. SMPL: A Skinned Multi-Person Linear Model. ACM Trans. Graph. 34, 6, Article 248 (2015). https://doi.org/10.1145/2816795.2818013
[26]
N. Magnenat-Thalmann, R. Laperrière, and D. Thalmann. 1989. Joint-Dependent Local Deformations for Hand Animation and Object Grasping. In Proc. Graph. Interface. 26--33.
[27]
Rahul Narain, Armin Samii, and James F. O'Brien. 2012. Adaptive Anisotropic Remeshing for Cloth Simulation. ACM Trans. Graph. 31, 6, Article 152 (2012). https://doi.org/10.1145/2366145.2366171
[28]
Andrew Nealen, Matthias Müller, Richard Keiser, Eddy Boxerman, and Mark Carlson. 2006. Physically Based Deformable Models in Computer Graphics. Comput. Graph. Forum 25, 4 (2006), 809--836. https://doi.org/10.1111/j.1467-8659.2006.01000.x
[29]
Xiaoyu Pan, Jiaming Mai, Xinwei Jiang, Dongxue Tang, Jingxiang Li, Tianjia Shao, Kun Zhou, Xiaogang Jin, and Dinesh Manocha. 2022. Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks. In ACM SIGGRAPH. Article 11. https://doi.org/10.1145/3528233.3530709
[30]
Chaitanya Patel, Zhouyingcheng Liao, and Gerard Pons-Moll. 2020. TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 7363--7373. https://doi.org/10.1109/CVPR42600.2020.00739
[31]
Ekagra Ranjan, Soumya Sanyal, and Partha Pratim Talukdar. 2019. ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations. In Proc. AAAI Conf. Artif. Intell. https://api.semanticscholar.org/CorpusID:208158156
[32]
Igor Santesteban, Miguel Otaduy, Nils Thuerey, and Dan Casas. 2022b. ULNeF: Untangled Layered Neural Fields for Mix-and-Match Virtual Try-On. In Proc. Adv. Neural Inf. Process. Syst., Vol. 35. 12110--12125.
[33]
Igor Santesteban, Miguel A. Otaduy, and Dan Casas. 2019. Learning-Based Animation of Clothing for Virtual Try-On. Comput. Graph. Forum 38, 2 (2019), 355--366. https://doi.org/10.1111/cgf.13643
[34]
Igor Santesteban, Miguel A. Otaduy, and Dan Casas. 2022a. SNUG: Self-Supervised Neural Dynamic Garments. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 8130--8140. https://doi.org/10.1109/CVPR52688.2022.00797
[35]
Igor Santesteban, Nils Thuerey, Miguel A. Otaduy, and Dan Casas. 2021. Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 11758--11768. https://doi.org/10.1109/CVPR46437.2021.01159
[36]
Rui Shi, Tianxing Li, and Yasushi Yamaguchi. 2022. Output-targeted baseline for neuron attribution calculation. Image Vis. Comput. 124 (2022), 104516. https://doi.org/10.1016/j.imavis.2022.104516
[37]
Leonid Sigal, Moshe Mahler, Spencer Diaz, Kyna McIntosh, Elizabeth Carter, Timothy Richards, and Jessica Hodgins. 2015. A Perceptual Control Space for Garment Simulation. ACM Trans. Graph. 34, 4, Article 117 (2015). https://doi.org/10.1145/2766971
[38]
Carsten Stoll, Juergen Gall, Edilson de Aguiar, Sebastian Thrun, and Christian Theobalt. 2010. Video-Based Reconstruction of Animatable Human Characters. In ACM SIGGRAPH Asia. Article 139. https://doi.org/10.1145/1866158.1866161
[39]
Min Tang, Huamin Wang, Le Tang, Ruofeng Tong, and Dinesh Manocha. 2016. CAMA: Contact-Aware Matrix Assembly with Unified Collision Handling for GPU-based Cloth Simulation. Comput. Graph. Forum 35, 2 (2016), 511--521. https://doi.org/10.1111/cgf.12851
[40]
Garvita Tiwari, Bharat Lal Bhatnagar, Tony Tung, and Gerard Pons-Moll. 2020. SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing. In Proc. Eur. Conf. Comput. Vis., Vol. 12348.1-18. https://doi.org/10.1007/978-3-030-58580-8_1
[41]
Tzvetomir Vassilev, Spanlang Bernhard, and Chrysanthou. Yiorgos. 2001. Fast Cloth Animation on Walking Avatars. Computer Graphics Forum 20, 3 (2001), 260--267. https://doi.org/10.1111/1467-8659.00518
[42]
Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. In Proc. Int. Conf. Learn. Representations. https://openreview.net/forum?id=rJXMpikCZ
[43]
Raquel Vidaurre, Igor Santesteban, Elena Garces, and Dan Casas. 2020. Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On. Comput. Graph. Forum 39, 8 (2020), 145--156. https://doi.org/10.1111/cgf.14109
[44]
Huamin Wang. 2021. GPU-Based Simulation of Cloth Wrinkles at Submillimeter Levels. ACM Trans. Graph. 40, 4, Article 169 (2021). https://doi.org/10.1145/3450626.3459787
[45]
Tuanfeng Y. Wang, Duygu Ceylan, Jovan Popović, and Niloy J. Mitra. 2018. Learning a Shared Shape Space for Multimodal Garment Design. ACM Trans. Graph. 37, 6, Article 203 (2018). https://doi.org/10.1145/3272127.3275074
[46]
Longhua Wu, Botao Wu, Yin Yang, and Huamin Wang. 2020. A Safe and Fast Repulsion Method for GPU-Based Cloth Self Collisions. ACM Trans. Graph. 40, 1, Article 5 (2020). https://doi.org/10.1145/3430025
[47]
Shan Yang, Zherong Pan, Tanya Amert, Ke Wang, Licheng Yu, Tamara Berg, and Ming C. Lin. 2018. Physics-Inspired Garment Recovery from a Single-View Image. ACM Trans. Graph. 37, 5, Article 170 (2018). https://doi.org/10.1145/3026479
[48]
Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, and Jure Leskovec. 2018. Hierarchical Graph Representation Learning with Differentiable Pooling. In Proc. Adv. Neural Inf. Process. Syst. 4805--4815.

Index Terms

  1. Efficient Deformation Learning of Varied Garments with a Structure-Preserving Multilevel Framework

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image Proceedings of the ACM on Computer Graphics and Interactive Techniques
      Proceedings of the ACM on Computer Graphics and Interactive Techniques  Volume 7, Issue 1
      May 2024
      399 pages
      EISSN:2577-6193
      DOI:10.1145/3665094
      Issue’s Table of Contents
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 13 May 2024
      Published in PACMCGIT Volume 7, Issue 1

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. Attribution analysis
      2. Clothing deformation
      3. Graph pooling
      4. Nerual network

      Qualifiers

      • Research-article
      • Research
      • Refereed

      Data Availability

      Network architecture, loss functions, dataset generation, network training, replication details https://dl.acm.org/doi/10.1145/3651286#psdunet-supp-cr.pdf

      Funding Sources

      • JSPS KAKENHI
      • Beijing Natural Science Foundation
      • Beijing Natural Science Foundation

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • 0
        Total Citations
      • 111
        Total Downloads
      • Downloads (Last 12 months)111
      • Downloads (Last 6 weeks)7
      Reflects downloads up to 16 Feb 2025

      Other Metrics

      Citations

      View Options

      Login options

      Full Access

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media