Journal of the Korea Computer Graphics Society (한국컴퓨터그래픽스학회논문지)

Korea Computer Graphics Society (한국컴퓨터그래픽스학회)
권호 표지
DOI QR코드

DOI QR Code

Estimating Simulation Parameters for Kint Fabrics from Static Drapes

정적 드레이프를 이용한 니트 옷감의 시뮬레이션 파라미터 추정

  • Received : 2020.10.05
  • Accepted : 2020.11.20
  • Published : 2020.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

We present a supervised learning method that estimates the simulation parameters required to simulate the fabric from the static drape shape of a given fabric sample. The static drape shape was inspired by Cusick's drape, which is used in the apparel industry to classify fabrics according to their mechanical properties. The input vector of the training model consists of the feature vector extracted from the static drape and the density value of a fabric specimen. The output vector consists of six simulation parameters that have a significant influence on deriving the corresponding drape result. To generate a plausible and unbiased training data set, we first collect simulation parameters for 400 knit fabrics and generate a Gaussian Mixed Model (GMM) generation model from them. Next, a large number of simulation parameters are randomly sampled from the GMM model, and cloth simulation is performed for each sampled simulation parameter to create a virtual static drape. The generated training data is fitted with a log-linear regression model. To evaluate our method, we check the accuracy of the training results with a test data set and compare the visual similarity of the simulated drapes.

본 연구에서는 주어진 옷감 시료의 정적 드레이프 모양으로부터 해당 옷감을 시뮬레이션하기 위해 필요한 시뮬레이션 파라미터를 추정하는 데이터 기반 학습법을 제시한다. 정적 드레이프의 모양을 형성하기 위해 의류 산업계에서 옷감을 물성에 따라 분류하기 위해 사용하는 쿠식 드레이프 (Cusick's drape)에서 착안한 방법을 사용한다. 학습 모델의 입력 벡터는 특정 옷감의 정적 드레이프 모양에서 추출한 특징 벡터와 옷감의 밀도 값으로 구성되고, 출력 벡터는 해당 드레이프 결과를 도출하는 여섯가지 시뮬레이션 파라미터로 구성된다. 실제에 가깝고 편향되지 않은 학습 데이터를 생성하고자 먼저 400가지의 실제 니트 옷감에 대한 시뮬레이션 파라미터를 수집하고 이로부터 GMM (Gaussian mixture model) 생성 모델을 만든다. 다음, GMM 확률분포에 따라 대량의 시뮬레이션 파라미터를 무작위 샘플링한다. 샘플링된 각각의 시뮬레이션 파라미터에 대해 옷감 시뮬레이션을 수행하여 가상의 정적 드레이프 결과를 만들고 이로부터 특징 벡터를 추출한다. 생성된 데이터를 로그선형회기(log-linear regression) 모델로 피팅한다. 학습의 수치적 정확도를 검증하고 시뮬레이션 결과의 시각적 유사도를 비교하여 제시된 방법의 유용성을 확인한다.

Keywords

References

  1. G. E. Cusick, "The dependence of fabric drape on bending and shear stiffness," Journal of the Textile Institute Transactions, vol. 56, no. 11, pp. T596-T606, 1965. https://doi.org/10.1080/19447026508662319
  2. K. S. Bhat, C. D. Twigg, J. K. Hodgins, P. K. Khosla, Z. Popovic, and S. M. Seitz, "Estimating cloth simulation parameters from video," in Proceedings of the 2003 ACM SIG-GRAPH/Eurographics symposium on Computer animation, 2003, pp. 37-51.
  3. H. Wang, J. F. O'Brien, and R. Ramamoorthi, "Data-driven elastic models for cloth: modeling and measurement," ACM transactions on graphics (TOG), vol. 30, no. 4, pp. 1-12, 2011.
  4. E. Miguel, D. Bradley, B. Thomaszewski, B. Bickel, W. Matusik, M. A. Otaduy, and S. Marschner, "Data-driven estimation of cloth simulation models," in Computer Graphics Forum, vol. 31, no. 2pt2. Wiley Online Library, 2012, pp. 519-528. https://doi.org/10.1111/j.1467-8659.2012.03031.x
  5. D. Mongus, B. Repnik, M. Mernik, and B. Zalik, "A hybrid evolutionary algorithm for tuning a cloth-simulation model," Applied Soft Computing, vol. 12, no. 1, pp. 266-273, 2012. https://doi.org/10.1016/j.asoc.2011.08.047
  6. S. Yang, Z. Pan, T. Amert, K. Wang, L. Yu, T. Berg, and M. C. Lin, "Physics-inspired garment recovery from a single-view image," ACM Transactions on Graphics (TOG), vol. 37, no. 5, pp. 1-14, 2018.
  7. J. Hu and Y.-F. Chan, "Effect of fabric mechanical properties on drape," Textile Research Journal, vol. 68, no. 1, pp. 57-64, 1998. https://doi.org/10.1177/004051759806800107
  8. T. Shyr, P. Wang, and K. Cheng, "A comparison of the key parameters affecting dynamic and static drape coefficients of natural fibre woven fabrics by a newly devised dynamic drape automatic measuring system," Fibres and Textiles in Eastern Europe, vol. 15, no. 3, p. 81, 2007.
  9. B. Al-Gaadi, F. Goktepe, and M. Halasz, "A new method in fabric drape measurement and analysis of the drape formation process," Textile Research Journal, vol. 82, no. 5, pp. 502-512, 2012. https://doi.org/10.1177/0040517511420760
  10. R. Sanad and T. Cassidy, "Investigating garment drape behaviour," Journal of Fiber bioengineering and informatics, vol. 8, no. 1, pp. 47-56, 2015. https://doi.org/10.3993/jfbi03201505
  11. K. L. Bouman, B. Xiao, P. Battaglia, and W. T. Freeman, "Estimating the material properties of fabric from video," in Proceedings of the IEEE international conference on computer vision, 2013, pp. 1984-1991.
  12. W. Bi, P. Jin, H. Nienborg, and B. Xiao, "Estimating mechanical properties of cloth from videos using dense motion trajectories: Human psychophysics and machine learning," Journal of vision, vol. 18, no. 5, pp. 12-12, 2018. https://doi.org/10.1167/18.5.12
  13. S. Kawabata, "The standardization and analysis of hand evaluation," in Effect of mechanical and physical properties on fabric hand. Elsevier, 2005, pp. 389-442.
  14. D. E. Breen, D. H. House, and M. J. Wozny, "Predicting the drape of woven cloth using interacting particles," in Proceedings of the 21st annual conference on Computer graphics and interactive techniques, 1994, pp. 365-372.
  15. A. Davis, K. L. Bouman, J. G. Chen, M. Rubinstein, F. Durand, and W. T. Freeman, "Visual vibrometry: Estimating material properties from small motion in video," in Proceedings of the ieee conference on computer vision and pattern recognition, 2015, pp. 5335-5343.
  16. S. Yang, J. Liang, and M. C. Lin, "Learning-based cloth material recovery from video," in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 4383-4393.
  17. E. Carrera-Gallissa, X. Capdevila, and J. Valldeperas, "Evaluating drape shape in woven fabrics," The Journal of The Textile Institute, vol. 108, no. 3, pp. 325-336, 2017. https://doi.org/10.1080/00405000.2016.1166804
  18. A. Lam, A. Raheja, and M. Govindaraj, "Neural network models for fabric drape prediction," in 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541), vol. 4, 2004, pp. 2925-2929.
  19. M. Halasz, "Sylvie® 3d drape tester-new system for measuring fabric drape," 2006.
  20. N. Kenkare, T. A. Lamar, P. Pandurangan, and J. Eischen, "Enhancing accuracy of drape simulation. part i: Investigation of drape variability via 3d scanning," Journal of the Textile Institute, vol. 99, no. 3, pp. 211-218, 2008. https://doi.org/10.1080/00405000701489222
  21. V. Glombikova and K. Zdenek, "Drape evaluation by the 3d drape scanner," Tekstil ve Konfeksiyon, vol. 24, no. 3, pp. 279-285, 2014.
  22. A. Hussain, Y. Zhong, T. Naveed, Z. Yu, Z. Xi, and W. Ge, "A new approach to evaluate fabric hand based on three-dimensional drape model," Autex Research Journal, vol. 20, no. 2, pp. 155-167, 2020. https://doi.org/10.2478/aut-2019-0011
  23. CLO Virtual Fashion Inc., "CLO," https://www.clo3d.com/, 2009-2020.
  24. D. Baraff and A. Witkin, "Large steps in cloth simulation," in Proceedings of the 25th annual conference on Computer graphics and interactive techniques, 1998, pp. 43-54.
  25. CLO Virtual Fashion Inc., "Fabric kit manual," https://support.clo3d.com/hc/en-us/articles/360041074334-Fabric-Kit-Manual, January 2020.
  26. H. Akaike, "Information theory and an extension of the maximum likelihood principle," in Selected papers of hirotugu akaike, 1998, pp. 199-213.