Papers
Topics
Authors
Recent
Search
2000 character limit reached

HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics

Published 14 Dec 2022 in cs.CV | (2212.07242v3)

Abstract: We propose a method that leverages graph neural networks, multi-level message passing, and unsupervised training to enable real-time prediction of realistic clothing dynamics. Whereas existing methods based on linear blend skinning must be trained for specific garments, our method is agnostic to body shape and applies to tight-fitting garments as well as loose, free-flowing clothing. Our method furthermore handles changes in topology (e.g., garments with buttons or zippers) and material properties at inference time. As one key contribution, we propose a hierarchical message-passing scheme that efficiently propagates stiff stretching modes while preserving local detail. We empirically show that our method outperforms strong baselines quantitatively and that its results are perceived as more realistic than state-of-the-art methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Layered-garment net: Generating multiple implicit garment layers from a single image. In ACCV, pages 3000–3017, 2022.
  2. Large steps in cloth simulation. In Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH ’98, page 43–54, New York, NY, USA, 1998. Association for Computing Machinery.
  3. Large steps in cloth simulation. In Proceedings of the 25th annual conference on Computer graphics and interactive techniques, pages 43–54, 1998.
  4. Cloth3d: clothed 3d humans. In European Conference on Computer Vision, pages 344–359. Springer, 2020.
  5. Pbns: Physically based neural simulator for unsupervised garment pose space deformation. arXiv preprint arXiv:2012.11310, 2020.
  6. Deepsd: Automatic deep skinning and pose space deformation for 3d garment animation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5471–5480, 2021.
  7. Estimating cloth simulation parameters from video. 2003.
  8. Robust treatment of collisions, contact and friction for cloth animation. In Proceedings of the 29th annual conference on Computer graphics and interactive techniques, pages 594–603, 2002.
  9. Accurate dissipative forces in optimization integrators. ACM Trans. Graph., 37(6), dec 2018.
  10. Implicit untangling: A robust solution for modeling layered clothing. ACM Trans. Graph., 38(4), jul 2019.
  11. Bi-stride multi-scale graph neural network for mesh-based physical simulation. arXiv preprint arXiv:2210.02573, 2022.
  12. SNARF: Differentiable forward skinning for animating non-rigid neural implicit shapes. In Proc. International Conference on Computer Vision (ICCV), pages 11574–11584, Piscataway, NJ, Oct. 2021. IEEE.
  13. Stable but responsive cloth. In ACM SIGGRAPH 2005 Courses, pages 1–es. 2005.
  14. Yarn-level simulation of woven cloth. ACM Trans. Graph., 33(6), nov 2014.
  15. SMPLicit: Topology-aware generative model for clothed people. In CVPR, 2021.
  16. MultiScale MeshGraphNets. arXiv preprint arXiv:2210.00612, 2022.
  17. Graph u-nets. In international conference on machine learning, pages 2083–2092. PMLR, 2019.
  18. Add: Analytically differentiable dynamics for multi-body systems with frictional contact. ACM Trans. Graph., 39(6), nov 2020.
  19. Discrete shells. In Proceedings of the 2003 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA ’03, page 62–67, Goslar, DEU, 2003. Eurographics Association.
  20. Drape: Dressing any person. ACM Transactions on Graphics (ToG), 31(4):1–10, 2012.
  21. Asynchronous contact mechanics. New York, NY, USA, 2009. ACM.
  22. Codimensional incremental potential contact. ACM Trans. Graph., 40(4), jul 2021.
  23. Foldsketch: Enriching garments with physically reproducible folds. ACM Transaction on Graphics, 37(4), 2018.
  24. Dig: Draping implicit garment over the human body. arXiv preprint arXiv:2209.10845, 2022.
  25. Diffcloth: Differentiable cloth simulation with dry frictional contact. ACM Trans. Graph., 42(1), oct 2022.
  26. Differentiable Cloth Simulation for Inverse Problems. Curran Associates Inc., Red Hook, NY, USA, 2019.
  27. Learning implicit templates for point-based clothed human modeling. In ECCV, 2022.
  28. Simulating continuum mechanics with multi-scale graph neural networks. arXiv preprint arXiv:2106.04900, 2021.
  29. SMPL: A skinned multi-person linear model. ACM Trans. Graphics (Proc. SIGGRAPH Asia), 34(6):248:1–248:16, Oct. 2015.
  30. Learning to dress 3d people in generative clothing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6469–6478, 2020.
  31. The power of points for modeling humans in clothing. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 10974–10984, Oct. 2021.
  32. Amass: Archive of motion capture as surface shapes. In Proceedings of the IEEE/CVF international conference on computer vision, pages 5442–5451, 2019.
  33. Example-based elastic materials. ACM Trans. Graph., 30(4), jul 2011.
  34. Data-driven estimation of cloth simulation models. Computer Graphics Forum, 31(2pt2):519–528, 2012.
  35. Computational design of skintight clothing. ACM Trans. Graph., 39(4):105, 2020.
  36. Adaptive anisotropic remeshing for cloth simulation. ACM Trans. Graph., 31(6), nov 2012.
  37. Adaptive anisotropic remeshing for cloth simulation. ACM transactions on graphics (TOG), 31(6):1–10, 2012.
  38. Predicting loose-fitting garment deformations using bone-driven motion networks. In ACM SIGGRAPH 2022 Conference Proceedings, pages 1–10, 2022.
  39. Tailornet: Predicting clothing in 3d as a function of human pose, shape and garment style. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7365–7375, 2020.
  40. Learning mesh-based simulation with graph networks. arXiv preprint arXiv:2010.03409, 2020.
  41. Learning to simulate complex physics with graph networks. In International Conference on Machine Learning, pages 8459–8468. PMLR, 2020.
  42. Learning-based animation of clothing for virtual try-on. Computer Graphics Forum, 38(2):355–366, 2019.
  43. SNUG: Self-supervised neural dynamic garments. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8140–8150, 2022.
  44. ULNeF: Untangled layered neural fields for mix-and-match virtual try-on. In Advances in Neural Information Processing Systems, (NeurIPS), 2022.
  45. Self-supervised collision handling via generative 3d garment models for virtual try-on. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 11763–11773, June 2021.
  46. Deepcloth: Neural garment representation for shape and style editing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  47. I-cloth: Incremental collision handling for gpu-based interactive cloth simulation. ACM Transactions on Graphics (TOG), 37(6):1–10, 2018.
  48. Elastically deformable models. In Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH ’87, page 205–214, New York, NY, USA, 1987. Association for Computing Machinery.
  49. Asynchronous cloth simulation. 2008.
  50. A simple approach to nonlinear tensile stiffness for accurate cloth simulation. ACM Trans. Graph., 28(4), sep 2009.
  51. Data-driven elastic models for cloth: Modeling and measurement. In ACM SIGGRAPH 2011 Papers, SIGGRAPH ’11, New York, NY, USA, 2011. Association for Computing Machinery.
  52. Point-based modeling of human clothing. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 14718–14727, 2021.
  53. Motion guided deep dynamic 3d garments. arXiv preprint arXiv:2209.11449, 2022.
Citations (42)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up