Coefficient Prediction for Physically-based Cloth Simulation Using Deep learning

Makara Mao, Hongly Va, Min Hong

Abstract


Physically-based cloth simulation involves modeling cloth as a collection of particles or nodes connected by various types of constraints. These particles interact with each other and the environment, such as gravity or collisions, to accurately simulate the cloth's behavior. One essential component of such simulations is the set of material parameters or coefficients that dictate the cloth's physical properties, such as stiffness and damping. Deep learning-based coefficient prediction in physically-based cloth simulation involves using machine learning techniques, specifically deep neural networks, to predict the material parameters of cloth from its geometric and physical properties. The deep learning model is trained using a dataset of simulated cloth instances, where the material parameters are known. The input to the model is a set of geometric and physical properties of the cloth, such as the dimensions, orientation, and velocity. The output of the model is the set of material parameters that best represent the cloth's behavior under these conditions. This paper proposes a deep learning method for predicting these coefficients using a multi-label video classification approach. The training data is generated from a physics-based simulator, and the method is evaluated on some cloth simulations, such as fabric falling down, fabric with collision, and fabric affected by airflow. The cloth movement dataset is generated from a mass-spring-based simulation. The results show that the transformer model has much higher accuracy than other models. This study provides a promising approach for predicting the coefficients of virtual cloth in physically-based simulations.

Keywords


Deep learning; computer vision; cloth simulation; transformer; LSTM; GRU

Full Text:

PDF

References


M. Bhatia, N. Manini, F. Biasioli, and L. Cappellin, "Calculated rate coefficients between CI-MS reagent ions and organosulfur compounds causing food taints and off-flavours," International Journal of Mass Spectrometry, vol. 478, p. 116860, Aug. 2022, doi: 10.1016/j.ijms.2022.116860.

S. M. Alshammari, J.-L. Le Garrec, and J. B. A. Mitchell, "Electron collisions with dimethylamine and trimethylamine molecules and molecular ions," International Journal of Mass Spectrometry, vol. 474, p. 116802, Apr. 2022, doi: 10.1016/j.ijms.2022.116802.

J. S. Bhanot et al., "Adaptation and operation of a quadrupole/time-of-flight tandem mass spectrometer for high mass ion/ion reaction studies," International Journal of Mass Spectrometry, vol. 478, p. 116874, Aug. 2022, dol: 10.1016/j.ijms.2022.116874.

N. Sirigiri et al., "Factors controlling the physical properties of an organic ionic plastic crystal," Materials Today Physics, vol. 22, p. 100603, Jan. 2022. doi: 10.1016/j.mtphys.2022.100603.

Z. Ballard, C. Brown, A. M. Madni, and A. Ozcan, "Machine learning and computation-enabled intelligent sensor design," Nature News, Jun. 2021. doi: 10.1038/s42256-021-00360-9.

Zimmerling, Clemens, Daniel Trippe, Benedikt Fengler, and Luise Kärger. "An approach for rapid prediction of textile draping results for variable composite component geometries using deep neural networks," In AIP conference proceedings, vol. 2113, no. 1, p. 020007. Jul. 2019. doi: 10.1063/1.5112512.

J. Jiang, B. Sheng, P. Li, L. Ma, X. Tong, and E. Wu, "Real-time hair simulation with heptadiagonal decomposition on mass spring system," Graphical Models, vol. 111, p. 101077, Sep. 2020. doi: 10.1016/j.gmod.2020.101077.

J. Flotyński, K. Walczak, and M. Krzyszkowski, "Composing customized web 3D animations with semantic queries," Graphical Models, vol. 107, p. 101052, Jan. 2020. doi: 10.1016/j.gmod.2019.101052.

C.-Y. Liu, L.-J. Chiou, C.-C. Li, and X.-W. Ye, "Analysis of Beijing Tianjin Hebei regional credit system from the perspective of big data credit reporting," Journal of Visual Communication and Image Representation, vol. 59, pp. 300–308, Feb. 2019, doi: 10.1016/j.jvcir.2019.01.018.

N. Agarwal and S. Chauhan, "Amplifying Employability Skills to Create Co-Working Space for Human and Cobots in the E-Commerce Industry," Procedia Computer Science, vol. 214, pp. 1040–1048, 2022, doi: 10.1016/j.procs.2022.11.275.

B. Gaudenzi, L. Mola, and C. Rossignoli, "Hitting or missing the target: Resources and capabilities for alternative e-commerce pathways in the fashion industry," Industrial Marketing Management, vol. 93, pp. 124–136, Feb. 2021, doi: 10.1016/j.indmarman.2020.12.016.

A. Pandey and U. C. Pati, "Image mosaicing: A deeper insight," Image and Vision Computing, vol. 89, pp. 236–257, Aug. 2019, doi: 10.1016/j.imavis.2019.07.002.

N. K. S. Behera, P. K. Sa, S. Bakshi, and R. P. Padhy, "Person re-identification: A taxonomic survey and the path ahead," Image and Vision Computing, vol. 122, p. 104432, Mar. 2022, doi: 10.1016/j.imavis.2022.104432.

N. Moniz and L. Torgo, "A review on web content popularity prediction: Issues and open challenges," Online Social Networks and Media, vol. 12, pp. 1–20, Jul. 2019, doi: 10.1016/j.osnem.2019.05.002.

M. M. Lazar and L. Wan, "Remediatisation, media interdiscursivity and ideological ambivalence in online news reports on sexual assault," Discourse, Context & Media, vol. 48, p. 100620, Aug. 2022. doi: 10.1016/j.dcm.2022.100620.

C. Ilbury, "Discourses of social media amongst youth: An ethnographic perspective," Discourse, Context & Media, vol. 48, p. 100625, Aug. 2022. doi: 10.1016/j.dcm.2022.100625.

T. Yıldız, "The most effective element in conceptualization is social interaction, not source or modality: A new model of the conceptual development in children," Learning, Culture and Social Interaction, vol. 24, p. 100377, Mar. 2020. doi: 10.1016/j.lcsi.2019.100377.

X. Tong, K. Myszkowski, and J. Huang, 'Foreword to the special section on the international conference on computer-aided design and computer graphics (CAD/Graphics) 2019," Computers & Graphics, vol. 86, pp. A5–A6, Feb. 2020 doi: 10.1016/j.cag.2019.12.002.

Q. Jing, K. Sasa, C. Chen, Y. Yin, H. Yasukawa, and D. Terada, "Analysis of ship maneuvering difficulties under severe weather based on onboard measurements and realistic simulation of ocean environment," Ocean Engineering, vol. 221, p. 108524, Feb. 2021. doi: 10.1016/j.oceaneng.2020.108524.

L. Accorsi, A. Lodi, and D. Vigo, "Guidelines for the computational testing of machine learning approaches to vehicle routing problems," Operations Research Letters, vol. 50, no. 2, pp. 229–234, Mar. 2022. doi: 10.1016/j.orl.2022.01.018.

N. Sirigiri et al., "Factors controlling the physical properties of an organic ionic plastic crystal," Materials Today Physics, vol. 22, p. 100603, Jan. 2022. doi: 10.1016/j.mtphys.2022.100603.

V. Terziyan, D. Malyk, M. Golovianko, and V. Branytskyi, "Hyper-flexible Convolutional Neural Networks based on Generalized Lehmer and Power Means," Neural Networks, vol. 155, pp. 177–203, Nov. 2022. Doi: 10.1016/j.neunet.2022.08.017

S. Nag, M. Basu, S. Sanyal, A. Banerjee, and D. Ghosh, "On the application of deep learning and multifractal techniques to classify emotions and instruments using Indian Classical Music," Physica A: Statistical Mechanics and its Applications, vol. 597, p. 127261, Jul. 2022.doi: 10.1016/j.physa.2022.127261

Y. Feng, Y. Yang, W. Deng, H. Chen, and T. Ran, "SyntaLinker-Hybrid: A deep learning approach for target specific drug design," Artificial Intelligence in the Life Sciences, vol. 2, p. 100035, Dec. 2022, doi: 10.1016/j.ailsci.2022.100035.

R. Codina and Ö. Türk, "Modal analysis of elastic vibrations of incompressible materials using a pressure-stabilized finite element method," Finite Elements in Analysis and Design, vol. 206, p. 103760, Sep. 2022. doi: 10.1016/j.finel.2022.103760.

Z.-X. Zou, S.-S. Huang, T.-J. Mu, and Y.-P. Wang, "ObjectFusion: Accurate object-level SLAM with neural object priors," Graphical Models, vol. 123, p. 101165, Sep. 2022, doi: 10.1016/j.gmod.2022.101165.

H. Wang, B. Ma, J. Cao, X. Liu, and H. Huang, "Deep functional maps for simultaneously computing direct and symmetric correspondences of 3D shapes," Graphical Models, vol. 123, p. 101163, Sep. 2022, doi: 10.1016/j.gmod.2022.101163.

Y.-W. Zhang, B.-B. Qin, Y. Chen, Z. Ji, and C. Zhang, "Portrait relief generation from 3D Object," Graphical Models, vol. 102, pp. 10–18, Mar. 2019, doi: 10.1016/j.gmod.2019.01.002.

A. Chekir, "A deep architecture for log-Euclidean Fisher vector end-to-end learning with application to 3D point cloud classification," Graphical Models, vol. 123, p. 101164, Sep. 2022. doi: 10.1016/j.gmod.2022.101164.

O. Pueyo, X. Pueyo, and G. Patow, "An overview of generalization techniques for street networks," Graphical Models, vol. 106, p. 101049, Nov. 2019. doi: 10.1016/j.gmod.2019.101049.

D. Mahapatra, A. Poellinger, and M. Reyes, "Interpretability-Guided Inductive Bias For Deep Learning Based Medical Image," Medical Image Analysis, vol. 81, p. 102551, Oct. 2022. doi: 10.1016/j.media.2022.102551.

C. ViÅŸan et al., "Automated circuit sizing with multi-objective optimization based on differential evolution and Bayesian inference," Knowledge-Based Systems, vol. 258, p. 109987, Dec. 2022. doi: 10.1016/j.knosys.2022.109987.

Vaswani, Ashish, Noam M. Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin. “Attention is All you Need.†NIPS, 2017.




DOI: http://dx.doi.org/10.18517/ijaseit.13.4.19019

Refbacks

  • There are currently no refbacks.


Published by INSIGHT - Indonesian Society for Knowledge and Human Development