Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Spatially Adaptive Cloth Regression with Implicit Neural Representations (2311.16344v1)

Published 27 Nov 2023 in cs.CV and cs.GR

Abstract: The accurate representation of fine-detailed cloth wrinkles poses significant challenges in computer graphics. The inherently non-uniform structure of cloth wrinkles mandates the employment of intricate discretization strategies, which are frequently characterized by high computational demands and complex methodologies. Addressing this, the research introduced in this paper elucidates a novel anisotropic cloth regression technique that capitalizes on the potential of implicit neural representations of surfaces. Our first core contribution is an innovative mesh-free sampling approach, crafted to reduce the reliance on traditional mesh structures, thereby offering greater flexibility and accuracy in capturing fine cloth details. Our second contribution is a novel adversarial training scheme, which is designed meticulously to strike a harmonious balance between the sampling and simulation objectives. The adversarial approach ensures that the wrinkles are represented with high fidelity, while also maintaining computational efficiency. Our results showcase through various cloth-object interaction scenarios that our method, given the same memory constraints, consistently surpasses traditional discrete representations, particularly when modelling highly-detailed localized wrinkles.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (64)
  1. David Baraff and Andrew Witkin. 1998. Large steps in cloth simulation. In Proceedings of the 25th annual conference on Computer graphics and interactive techniques - SIGGRAPH ’98. ACM Press, New York, New York, USA, 43–54. https://doi.org/10.1145/280814.280821
  2. Tracks: toward directable thin shells. ACM Transactions on Graphics (TOG) 26, 3 (2007), 50–es.
  3. CLOTH3D: Clothed 3D Humans. (dec 2019). arXiv:1912.02792 http://arxiv.org/abs/1912.02792
  4. PBNS: physically based neural simulator for unsupervised garment pose space deformation. arXiv preprint arXiv:2012.11310 (2020).
  5. Simulation of clothing with folds and wrinkles. In ACM SIGGRAPH 2005 Courses on - SIGGRAPH ’05. ACM Press, New York, New York, USA, 3. https://doi.org/10.1145/1198555.1198573
  6. Juan J Casafranca and Miguel A Otaduy. 2022. Voronoi Filters for Simulation Enrichment. In Computer Graphics Forum, Vol. 41. Wiley Online Library, 43–51.
  7. Dan Casas and Miguel A Otaduy. 2018. Learning nonlinear soft-tissue dynamics for interactive avatars. PACMCGIT (2018).
  8. SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes. (apr 2021). arXiv:2104.03953 http://arxiv.org/abs/2104.03953
  9. Fine wrinkling on coarsely meshed thin shells. ACM Transactions on Graphics (TOG) 40, 5 (2021), 1–32.
  10. Modeling friction and air effects between cloth and deformable bodies. ACM Transactions on Graphics (TOG) 32, 4 (2013), 1–8.
  11. Cloth and skin deformation with a triangle mesh based convolutional neural network. ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA 2020 (2020), 123–134. https://doi.org/10.1111/cgf.14107
  12. Kwang-Jin Choi and Hyeong-Seok Ko. 2005. Stable but responsive cloth. In ACM SIGGRAPH 2005 Courses on - SIGGRAPH ’05. ACM Press, New York, New York, USA, 1. https://doi.org/10.1145/1198555.1198571
  13. Yarn-level simulation of woven cloth. ACM Transactions on Graphics 33, 6 (nov 2014), 1–11. https://doi.org/10.1145/2661229.2661279
  14. Modeling and data-driven parameter estimation for woven fabrics. In Proceedings of the ACM SIGGRAPH / Eurographics Symposium on Computer Animation. ACM, New York, NY, USA, 1–11. https://doi.org/10.1145/3099564.3099577
  15. Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates. (jun 2020). arXiv:2006.07818 http://arxiv.org/abs/2006.07818
  16. A Fast Finite Element Solution for Cloth Modelling. In Proceedings of the 11th Pacific Conference on Computer Graphics and Applications (PG ’03). IEEE Computer Society, USA, 244.
  17. Vivace: a practical gauss-seidel method for stable soft body dynamics. ACM Trans. Graph. 35, 6 (2016), 214–1.
  18. Latent‐space Dynamics for Reduced Deformable Simulation. Computer Graphics Forum 38, 2 (may 2019), 379–391. https://doi.org/10.1111/cgf.13645
  19. CHARMS: A simple framework for adaptive simulation. ACM transactions on graphics (TOG) 21, 3 (2002), 281–290.
  20. DRAPE. ACM Transactions on Graphics 31, 4 (aug 2012), 1–10. https://doi.org/10.1145/2185520.2185531
  21. GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping. (nov 2018). arXiv:1811.10983 http://arxiv.org/abs/1811.10983
  22. Garnet: A two-stream network for fast and accurate 3d cloth draping. In CVPR.
  23. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.
  24. Anisotropic elastoplasticity for cloth, knit and hair frictional contact. ACM Transactions on Graphics 36, 4 (jul 2017), 1–14. https://doi.org/10.1145/3072959.3073623
  25. A Pixel-Based Framework for Data-Driven Clothing. (dec 2018). arXiv:1812.01677 http://arxiv.org/abs/1812.01677
  26. Physics-inspired upsampling for cloth simulation in games. ACM Transactions on Graphics 30, 4 (jul 2011), 1–10. https://doi.org/10.1145/2010324.1964988
  27. Data-driven physics for human soft tissue animation. ACM Transactions on Graphics 36, 4 (jul 2017), 1–12. https://doi.org/10.1145/3072959.3073685
  28. Theodore Kim. 2020. A Finite Element Formulation of Baraff‐Witkin Cloth. Computer Graphics Forum 39, 8 (dec 2020), 171–179. https://doi.org/10.1111/cgf.14111
  29. Theodore Kim and David Eberle. 2020. Dynamic deformables: implementation and production practicalities. In ACM SIGGRAPH Courses.
  30. DeepWrinkles: Accurate and Realistic Clothing Modeling. (aug 2018). arXiv:1808.03417 http://arxiv.org/abs/1808.03417
  31. Medial ElasticsElastics: Efficient and Collision-Ready Deformation via Medial Axis Transform. ACM Transactions on Graphics 39, 3 (2020). https://doi.org/10.1145/3384515
  32. Yijing Li and Jernej Barbic. 2015. Stable Anisotropic Materials. IEEE Transactions on Visualization and Computer Graphics 21, 10 (oct 2015), 1129–1137. https://doi.org/10.1109/TVCG.2015.2448105
  33. Learning to dress 3d people in generative clothing. In CVPR.
  34. Unified particle physics for real-time applications. ACM Transactions on Graphics 33, 4 (jul 2014), 1–12. https://doi.org/10.1145/2601097.2601152
  35. Data-Driven Estimation of Cloth Simulation Models. Computer Graphics Forum 31, 2pt2 (may 2012), 519–528. https://doi.org/10.1111/j.1467-8659.2012.03031.x
  36. Modeling and Estimation of Energy-Based Hyperelastic Objects. Computer Graphics Forum 35, 2 (may 2016), 385–396. https://doi.org/10.1111/cgf.12840
  37. Matthias Müller and Nuttapong Chentanez. 2010. Wrinkle Meshes.. In Symposium on Computer Animation. Madrid, Spain, 85–91.
  38. Folding and crumpling adaptive sheets. ACM Transactions on Graphics 32, 4 (jul 2013), 1–8. https://doi.org/10.1145/2461912.2462010
  39. Adaptive anisotropic remeshing for cloth simulation. ACM Transactions on Graphics 31, 6 (nov 2012), 1–10. https://doi.org/10.1145/2366145.2366171
  40. 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. 7365–7375.
  41. Learning Mesh-Based Simulation with Graph Networks. (oct 2020). arXiv:2010.03409 http://arxiv.org/abs/2010.03409
  42. Adaptive tearing and cracking of thin sheets. ACM Transactions on Graphics 33, 4 (jul 2014), 1–9. https://doi.org/10.1145/2601097.2601132
  43. Olivier Rémillard and Paul G Kry. 2013. Embedded thin shells for wrinkle simulation. ACM Transactions on Graphics (TOG) 32, 4 (2013), 1–8.
  44. Animation wrinkling: augmenting coarse cloth simulations with realistic-looking wrinkles. ACM Transactions on Graphics (ToG) 29, 6 (2010), 1–8.
  45. Learning to simulate complex physics with graph networks. 37th International Conference on Machine Learning, ICML 2020 PartF16814 (2020), 8428–8437. arXiv:2002.09405
  46. Learning-based animation of clothing for virtual try-on. In CGF.
  47. Snug: Self-supervised neural dynamic garments. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8140–8150.
  48. Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On. (may 2021). arXiv:2105.06462 http://arxiv.org/abs/2105.06462
  49. High-order Differentiable Autoencoder for Nonlinear Model Reduction. (feb 2021). arXiv:2102.11026 http://arxiv.org/abs/2102.11026
  50. Homogenized yarn-level cloth. ACM Transactions on Graphics 39, 4 (jul 2020). https://doi.org/10.1145/3386569.3392412
  51. Mechanics-aware deformation of yarn pattern geometry. ACM Transactions on Graphics 40, 4 (aug 2021), 1–11. https://doi.org/10.1145/3450626.3459816
  52. Jos Stam. 2009. Nucleus: Towards a unified dynamics solver for computer graphics. In 2009 11th IEEE International Conference on Computer-Aided Design and Computer Graphics. IEEE, 1–11. https://doi.org/10.1109/CADCG.2009.5246818
  53. Realtime Simulation of Thin-Shell Deformable Materials using CNN-Based Mesh Embedding. (sep 2019). arXiv:1909.12354 http://arxiv.org/abs/1909.12354
  54. I-Cloth: Incremental collision handling for GPU-based interactive cloth simulation. SIGGRAPH Asia 2018 Technical Papers, SIGGRAPH Asia 2018 37, 6 (dec 2018), 1–10. https://doi.org/10.1145/3272127.3275005
  55. Continuum-based Strain Limiting. Computer Graphics Forum 28, 2 (apr 2009), 569–576. https://doi.org/10.1111/j.1467-8659.2009.01397.x
  56. Huamin Wang. 2021. GPU-based simulation of cloth wrinkles at submillimeter levels. ACM Transactions on Graphics 40, 4 (aug 2021), 1–14. https://doi.org/10.1145/3450626.3459787
  57. Example-based wrinkle synthesis for clothing animation. ACM SIGGRAPH 2010 Papers, SIGGRAPH 2010 (2010). https://doi.org/10.1145/1778765.1778844
  58. Example-based wrinkle synthesis for clothing animation. In ACM SIGGRAPH 2010 papers. 1–8.
  59. Data-Driven Elastic Models for Cloth: Modeling and Measurement. ACM Transactions on Graphics 30, 4 (jul 2011), 1–12. https://doi.org/10.1145/2010324.1964966
  60. Eulerian-on-lagrangian cloth simulation. ACM Transactions on Graphics 37, 4 (aug 2018), 1–11. https://doi.org/10.1145/3197517.3201281
  61. A safe and fast repulsion method for GPU-based cloth self collisions. ACM Transactions on Graphics (TOG) 40, 1 (2020), 1–18.
  62. Example-based Real-time Clothing Synthesis for Virtual Agents. (jan 2021). arXiv:2101.03088 http://arxiv.org/abs/2101.03088
  63. Dynamic Neural Garments. (feb 2021). arXiv:2102.11811 http://arxiv.org/abs/2102.11811
  64. Evgeny Zuenko and Matthias Harders. 2019. Wrinkles, folds, creases, buckles: Small-scale surface deformations as periodic functions on 3D meshes. IEEE Transactions on Visualization and Computer Graphics 26, 10 (2019), 3077–3088.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now