Abstract
While data-driven fluid simulation methods greatly replace the physics-based fluid solver and achieve high quality results, it is a challenge to get enough realistic effect with less time. The Huge neural network models brought by the complexity of fluid data need to calculate a large number of parameters from the convolutional and full-connected layers in the forward propagation process, which lead to very long inference time and cannot meet the real-time requirements. Our method is based on a structural pruning method to reduce the number of parameters of a general fluid neural network model that imposes the admm constraints on original loss on training process and removes the convlutional filters at a certain rate according to their importance. We show the high quality results for velocity field reconstruction and advancing time from reduced parameters using our pruned fluid model, which has only 30%–50% parameters of the original model and greatly improves the inference speed of the model. It is a big step towards high-accuracy real-time fluid simulation.
H. Xiang and S. Yu—contribute equally to this work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Yang, S., He, X., Zhu, B.: Learning physical constraints with neural projections. Adv. Neural. Inf. Process. Syst. 33, 5178–5189 (2020)
Wiewel, S., Kim, B., Azevedo, V.C., Solenthaler, B., Thuerey, N.: Latent space subdivision: stable and controllable time predictions for fluid flow. In: Computer Graphics Forum, vol. 39, pp. 15–25. Wiley Online Library (2020)
Xie, Y., Franz, E., Chu, M., Thuerey, N.: tempoGAN: a temporally coherent, volumetric GAN for super-resolution fluid flow. ACM Trans. Graph. (TOG) 37(4), 1–15 (2018)
Ummenhofer, B., Prantl, L., Thuerey, N., Koltun, V.: Lagrangian fluid simulation with continuous convolutions. In: International Conference on Learning Representations (2020)
Kim, B., Azevedo, V.C., Thuerey, N., Kim, T., Gross, M., Solenthaler, B.: Deep fluids: a generative network for parameterized fluid simulations (2018)
Chu, M., Thuerey, N., Seidel, H.P., Theobalt, C., Zayer, R.: Learning meaningful controls for fluids. ACM Trans. Graph. 40(4), 1–13 (2021)
Zhang, T., Ye, S., Zhang, Y., Wang, Y., Fardad, M.: Systematic weight pruning of DNNs using alternating direction method of multipliers (2018)
Bridson, R.: Fluid Simulation for Computer Graphics. AK Peters/CRC Press (2015)
Foster, N., Metaxas, D.N.: Controlling fluid animation. In: Computer Graphics International Conference, CGI 1997, Hasselt and Diepenbeek, Belgium, 23–27 June 1997, pp. 178–188. IEEE Computer Society (1997). https://doi.org/10.1109/CGI.1997.601299
Stam, J.: Stable fluids. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 121–128 (1999)
Harlow, F.H., Welch, J.E.: Numerical calculation of time-dependent viscous incompressible flow of fluid with free surface. phys. Fluids 8(12), 2182–2189 (1965)
Chentanez, N., Müller, M.: Real-time Eulerian water simulation using a restricted tall cell grid. In: ACM Siggraph 2011 Papers, pp. 1–10 (2011)
Zhu, B., Lu, W., Cong, M., Kim, B., Fedkiw, R.: A new grid structure for domain extension. ACM Trans. Graph. (TOG) 32(4), 1–12 (2013)
Xiao, Y., Chan, S., Wang, S., Zhu, B., Yang, X.: An adaptive staggered-tilted grid for incompressible flow simulation. ACM Trans. Graph. (TOG) 39(6), 1–15 (2020)
Macklin, M., Müller, M.: Position based fluids. ACM Trans. Graph. (TOG) 32(4), 1–12 (2013)
Müller, M., Charypar, D., Gross, M.: Particle-based fluid simulation for interactive applications. In: Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation, pp. 154–159. Citeseer (2003)
Cornelis, J., Ihmsen, M., Peer, A., Teschner, M.: IISPH-FLIP for incompressible fluids. In: Computer Graphics Forum, vol. 33, pp. 255–262. Wiley Online Library (2014)
Bender, J., Koschier, D.: Divergence-free SPH for incompressible and viscous fluids. IEEE Trans. Visual Comput. Graph. 23(3), 1193–1206 (2016)
Zhu, Y., Bridson, R.: Animating sand as a fluid. ACM Trans. Graph. (TOG) 24(3), 965–972 (2005)
Harlow, F.H.: The particle-in-cell method for numerical solution of problems in fluid dynamics. Technical report, Los Alamos National Lab. (LANL), Los Alamos, NM (United States) (1962)
Brackbill, J.U., Ruppel, H.M.: FLIP: a method for adaptively zoned, particle-in-cell calculations of fluid flows in two dimensions. J. Comput. Phys. 65(2), 314–343 (1986)
Jiang, C., Schroeder, C., Selle, A., Teran, J., Stomakhin, A.: The affine particle-in-cell method. ACM Trans. Graph. (TOG) 34(4), 1–10 (2015)
Fu, C., Guo, Q., Gast, T., Jiang, C., Teran, J.: A polynomial particle-in-cell method. ACM Trans. Graph. (TOG) 36(6), 1–12 (2017)
Chen, Q., Wang, Y., Wang, H., Yang, X.: Data-driven simulation in fluids animation: a survey. Virtual Reality Intell. Hardw. 3(2), 87–104 (2021)
Chu, M., Thuerey, N.: Data-driven synthesis of smoke flows with CNN-based feature descriptors. ACM Trans. Graph. (TOG) 36(4), 1–14 (2017)
Ladickỳ, L., Jeong, S., Solenthaler, B., Pollefeys, M., Gross, M.: Data-driven fluid simulations using regression forests. ACM Trans. Graph. (TOG) 34(6), 1–9 (2015)
Stanton, M., Humberston, B., Kase, B., O’Brien, J.F., Fatahalian, K., Treuille, A.: Self-refining games using player analytics. ACM Trans. Graph. (TOG) 33(4), 1–9 (2014)
Li, Y., Wu, J., Tedrake, R., Tenenbaum, J.B., Torralba, A.: Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids. arXiv preprint arXiv:1810.01566 (2018)
Sanchez-Gonzalez, A., Godwin, J., Pfaff, T., Ying, R., Leskovec, J., Battaglia, P.: Learning to simulate complex physics with graph networks. In: International Conference on Machine Learning, pp. 8459–8468. PMLR (2020)
Schenck, C., Fox, D.: SPNets: differentiable fluid dynamics for deep neural networks. In: Conference on Robot Learning, pp. 317–335. PMLR (2018)
Yang, C., Yang, X., Xiao, X.: Data-driven projection method in fluid simulation. Comput. Animat. Virtual Worlds 27(3–4), 415–424 (2016)
Tompson, J., Schlachter, K., Sprechmann, P., Perlin, K.: Accelerating Eulerian fluid simulation with convolutional networks. In: International Conference on Machine Learning, pp. 3424–3433. PMLR (2017)
Chu, J., Zafar, N.B., Yang, X.: A schur complement preconditioner for scalable parallel fluid simulation. ACM Trans. Graph. (TOG) 36(4), 1 (2017)
Gao, M., et al.: GPU optimization of material point methods. ACM Trans. Graph. (TOG) 37(6), 1–12 (2018)
Cui, H., Zhang, H., Ganger, G.R., Gibbons, P.B., Xing, E.P.: GeePS: scalable deep learning on distributed GPUs with a GPU-specialized parameter server. In: Proceedings of the Eleventh European Conference on Computer Systems, pp. 1–16 (2016)
McAdams, A., Sifakis, E., Teran, J.: A parallel multigrid poisson solver for fluids simulation on large grids. In: Symposium on Computer Animation, pp. 65–73 (2010)
Liu, H., Mitchell, N., Aanjaneya, M., Sifakis, E.: A scalable Schur-complement fluids solver for heterogeneous compute platforms. ACM Trans. Graph. (TOG) 35(6), 1–12 (2016)
Jung, H.R., Kim, S.T., Noh, J., Hong, J.M.: A heterogeneous CPU-GPU parallel approach to a multigrid poisson solver for incompressible fluid simulation. Comput. Animat. Virtual Worlds 24(3–4), 185–193 (2013)
Lentine, M., Zheng, W., Fedkiw, R.: A novel algorithm for incompressible flow using only a coarse grid projection. ACM Trans. Graph. (TOG) 29(4), 1–9 (2010)
Hu, Y., Li, T.M., Anderson, L., Ragan-Kelley, J., Durand, F.: Taichi: a language for high-performance computation on spatially sparse data structures. ACM Trans. Graph. (TOG) 38(6), 1–16 (2019)
Hu, Y., et al.: DiffTaichi: differentiable programming for physical simulation. arXiv preprint arXiv:1910.00935 (2019)
Treuille, A., Lewis, A., Popović, Z.: Model reduction for real-time fluids. ACM Trans. Graph. (TOG) 25(3), 826–834 (2006)
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)
He, Y., Kang, G., Dong, X., Fu, Y., Yang, Y.: Soft filter pruning for accelerating deep convolutional neural networks. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pp. 2234–2240. International Joint Conferences on Artificial Intelligence Organization (2018). https://doi.org/10.24963/ijcai.2018/309
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China under Grants 62272298, 61872241 and 62077037, in part by Shanghai Municipal Science and Technology Major Project under Grant 2021SHZDZX0102.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xiang, H., Yu, S., Li, P., Li, W., Wu, E., Sheng, B. (2022). SlimFliud-Net: Fast Fluid Simulation Using Admm Pruning. In: Magnenat-Thalmann, N., et al. Advances in Computer Graphics. CGI 2022. Lecture Notes in Computer Science, vol 13443. Springer, Cham. https://doi.org/10.1007/978-3-031-23473-6_45
Download citation
DOI: https://doi.org/10.1007/978-3-031-23473-6_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23472-9
Online ISBN: 978-3-031-23473-6
eBook Packages: Computer ScienceComputer Science (R0)