“Data-driven synthesis of smoke flows with CNN-based feature descriptors” by Manocha and Pan

  • ©Mengyu Chu and Nils Thuerey

Conference:


Type:


Title:

    Data-driven synthesis of smoke flows with CNN-based feature descriptors

Session/Category Title: Fluid Control & Synthesis


Presenter(s)/Author(s):


Moderator(s):



Abstract:


    We present a novel data-driven algorithm to synthesize high resolution flow simulations with reusable repositories of space-time flow data. In our work, we employ a descriptor learning approach to encode the similarity between fluid regions with differences in resolution and numerical viscosity. We use convolutional neural networks to generate the descriptors from fluid data such as smoke density and flow velocity. At the same time, we present a deformation limiting patch advection method which allows us to robustly track deformable fluid regions. With the help of this patch advection, we generate stable space-time data sets from detailed fluids for our repositories. We can then use our learned descriptors to quickly localize a suitable data set when running a new simulation. This makes our approach very efficient, and resolution independent. We will demonstrate with several examples that our method yields volumes with very high effective resolutions, and non-dissipative small scale details that naturally integrate into the motions of the underlying flow.

References:


    1. Gizem Akinci, Markus Ihmsen, Nadir Akinci, and Matthias Teschner. 2012. Parallel Surface Reconstruction for Particle-Based Fluids. Computer Graphics Forum 31, 6 (2012), 1797–1809. Google ScholarDigital Library
    2. Ryoichi Ando, Nils Thürey, and Chris Wojtan. 2015. A Dimension-reduced Pressure Solver for Liquid Simulations. Computer Graphics Forum 34, 2 (2015), 10.Google ScholarDigital Library
    3. Adam Bargteil, Tolga Goktekin, James O’brien, and John Strain. 2006. A semi-Lagrangian contouring method for fluid simulation. ACM Transactions on Graphics 25, 1 (2006), 19–38. Google ScholarDigital Library
    4. Christopher Batty and Robert Bridson. 2008. Accurate viscous free surfaces for buckling, coiling, and rotating liquids. In Proc. Symposium on Computer Animation. ACM/Eurographics, 219–228.Google Scholar
    5. Christopher Batty, Andres Uribe, Basile Audoly, and Eitan Grinspun. 2012. Discrete viscous sheets. ACM Transactions on Graphics (TOG) 31, 4 (2012), 113.Google ScholarDigital Library
    6. C Bishop. 2007. Pattern Recognition and Machine Learning. Springer.Google Scholar
    7. Robert Bridson. 2015. Fluid Simulation for Computer Graphics. CRC Press.Google Scholar
    8. Jane Bromley, James W Bentz, Léon Bottou, Isabelle Guyon, Yann LeCun, Cliff Moore, Eduard Säckinger, and Roopak Shah. 1993. Signature verification using a “Siamese” time delay neural network. Int. J. of Pattern Recognition and Artificial Intelligence 7, 04 (1993), 669–688. Google ScholarCross Ref
    9. Yunbo Cao, Jun Xu, Tie-Yan Liu, Hang Li, Yalou Huang, and Hsiao-Wuen Hon. 2006. Adapting ranking SVM to document retrieval. In Proc. Research and Development in Information Retrieval. ACM, 186–193. Google ScholarDigital Library
    10. O Chapelle, B Schölkopf, and A Zien. 2006. Semi-supervised learning, ser. Adaptive computation and machine learning. Cambridge, MA: The MIT Press.Google Scholar
    11. Sumit Chopra, Raia Hadsell, and Yann LeCun. 2005. Learning a similarity metric discriminatively, with application to face verification. In Conference on Computer Vision and Pattern Recognition, Vol. 1. IEEE, 539–546. Google ScholarDigital Library
    12. Ercan Erturk, Thomas C Corke, and Cihan Gökçöl. 2005. Numerical solutions of 2-D steady incompressible driven cavity flow at high Reynolds numbers. International Journal for Numerical Methods in Fluids 48, 7 (2005), 747–774. Google ScholarCross Ref
    13. Ronald Fedkiw, Jos Stam, and Henrik Wann Jensen. 2001. Visual Simulation of Smoke. In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH ’01). ACM, New York, NY, USA, 15–22. Google ScholarDigital Library
    14. Abhinav Golas, Rahul Narain, Jason Sewall, Pavel Krajcevski, Pradeep Dubey, and Ming Lin. 2012. Large-scale Fluid Simulation Using Velocity-vorticity Domain Decomposition. ACM Trans. Graph. 31, 6, Article 148 (Nov. 2012), 9 pages.Google ScholarDigital Library
    15. Takeo Igarashi, Tomer Moscovich, and John F. Hughes. 2005. As-rigid-as-possible Shape Manipulation. ACM Trans. Graph. 24, 3 (July 2005), 1134–1141. Google ScholarDigital Library
    16. Ondrej Jamriska, Jakub Fiser, Paul Asente, Jingwan Lu, Eli Shechtman, and Daniel Sykora. 2015. LazyFluids: appearance transfer for fluid animations. ACM Transactions on Graphics 34, 4 (2015), 92.Google ScholarDigital Library
    17. M. Kass and G. Miller. 1990. Rapid, Stable Fluid Dynamics for Computer Graphics. ACM Transactions on Graphics 24, 4 (1990), 49–55. Google ScholarDigital Library
    18. Byungmoon Kim, Yingjie Liu, Ignacio Llamas, and Jarek Rossignac. 2005. FlowFixer: Using BFECC for Fluid Simulation. In Proc. Conference on Natural Phenomena. Eurographics, 51–56.Google Scholar
    19. Theodore Kim, Nils Thürey, Doug James, and Markus Gross. 2008. Wavelet Turbulence for Fluid Simulation. ACM Transactions on Graphics 27 (3) (2008), 50:1–6.Google Scholar
    20. Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov. 2015. Siamese Neural Networks for One-Shot Image Recognition. In Conference on Computer Vision and Pattern Recognition, Vol. 37. IEEE.Google Scholar
    21. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems. NIPS, 1097–1105.Google Scholar
    22. Vivek Kwatra, David Adalsteinsson, Theodore Kim, Nipun Kwatra, Mark Carlson, and Ming C Lin. 2007. Texturing fluids. Visualization and Computer Graphics 13, 5 (2007), 939–952. Google ScholarDigital Library
    23. Vivek Kwatra, Irfan Essa, Aaron Bobick, and Nipun Kwatra. 2005. Texture optimization for example-based synthesis. ACM Transactions on Graphics 24, 3 (2005), 795–802. Google ScholarDigital Library
    24. Lubor Ladicky, SoHyeon Jeong, Barbara Solenthaler, Marc Pollefeys, and Markus Gross. 2015. Data-driven fluid simulations using regression forests. ACM Transactions on Graphics (TOG) 34, 6 (2015), 199.Google ScholarDigital Library
    25. Michael Lentine, Wen Zheng, and Ronald Fedkiw. 2010. A novel algorithm for incompressible flow using only a coarse grid projection. ACM Transactions on Graphics 29, 4 (2010), 114.Google ScholarDigital Library
    26. Chongyang Ma, Li-Yi Wei, Baining Guo, and Kun Zhou. 2009. Motion field texture synthesis. ACM Transactions on Graphics (TOG) 28, 5 (2009), 110.Google ScholarDigital Library
    27. Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. 2008. Introduction to Information Retrieval. Cambridge University Press, New York, NY, USA. Google ScholarCross Ref
    28. A. McAdams, E. Sifakis, and J. Teran. 2010. A Parallel Multigrid Poisson Solver for Fluids Simulation on Large Grids. In Proceedings of Symposium on Computer Animation. ACM/Eurographics, 65–74.Google Scholar
    29. Olivier Mercier, Cynthia Beauchemin, Nils Thuerey, Theodore Kim, and Derek Nowrouzezahrai. 2015. Surface Turbulence for Particle-based Liquid Simulations. ACM Trans. Graph. 34, 6, Article 202 (Oct. 2015), 10 pages. Google ScholarDigital Library
    30. Hossein Mobahi, Ronan Collobert, and Jason Weston. 2009. Deep learning from temporal coherence in video. In International Conference on Machine Learning. ACM, 737–744. Google ScholarDigital Library
    31. Ken Museth. 2013. VDB: High-resolution sparse volumes with dynamic topology. ACM Transactions on Graphics 32, 3 (2013), 27.Google ScholarDigital Library
    32. Rahul Narain, Vivek Kwatra, Huai-Ping Lee, Theodore Kim, Mark Carlson, and Ming C Lin. 2007. Feature-guided dynamic texture synthesis on continuous flows. In Proc. Rendering Techniques. Eurographics, 361–370.Google Scholar
    33. Rahul Narain, Jason Sewall, Mark Carlson, and Ming C. Lin. 2008. Fast Animation of Turbulence Using Energy Transport and Procedural Synthesis. ACM Transactions on Graphics 27, 5 (2008), article 166. Google ScholarDigital Library
    34. T. Pfaff, N. Thuerey, J. Cohen, S. Tariq, and M. Gross. 2010. Scalable fluid simulation using anisotropic turbulence particles. In ACM Transactions on Graphics, Vol. 29. ACM, 174. Google ScholarDigital Library
    35. Tobias Pfaff, Nils Thuerey, and Markus Gross. 2012. Lagrangian Vortex Sheets for Animating Fluids. ACM Transactions on Graphics 31, 4 (2012), 112.Google ScholarDigital Library
    36. Tobias Pfaff, Nils Thuerey, Andrew Selle, and Markus Gross. 2009. Synthetic Turbulence Using Artificial Boundary Layers. ACM Trans. Graph. 28, 5, Article 121 (Dec. 2009), 10 pages. Google ScholarDigital Library
    37. Stephen B. Pope. 2000. Turbulent Flows. Cambridge University Press. Google ScholarCross Ref
    38. Paul Scovanner, Saad Ali, and Mubarak Shah. 2007. A 3-dimensional Sift Descriptor and Its Application to Action Recognition. In Proceedings of the 15th ACM International Conference on Multimedia (MM ’07). 357–360. Google ScholarDigital Library
    39. Andrew Selle, Ronald Fedkiw, Byungmoon Kim, Yingjie Liu, and Jarek Rossignac. 2008. An Unconditionally Stable MacCormack Method. J. Sci. Comput. 35, 2–3 (June 2008), 350–371.Google ScholarDigital Library
    40. Andrew Selle, Nick Rasmussen, and Ronald Fedkiw. 2005. A vortex particle method for smoke, water and explosions. In ACM Transactions on Graphics (TOG), Vol. 24. ACM, 910–914. Google ScholarDigital Library
    41. Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).Google Scholar
    42. O. Sorkine, D. Cohen-Or, Y. Lipman, M. Alexa, C. Rössl, and H.-P. Seidel. 2004. Laplacian Surface Editing. In Proc. Symposium on Geometry Processing. ACM/Eurographics, 175–184. Google ScholarDigital Library
    43. Jos Stam. 1999. Stable Fluids. In Proc. SIGGRAPH. ACM, 121–128. Google ScholarDigital Library
    44. Jonathan Tompson, Kristofer Schlachter, Pablo Sprechmann, and Ken Perlin. 2016. Accelerating Eulerian Fluid Simulation With Convolutional Networks. arXiv preprint arXiv:1607.03597 (2016).Google Scholar
    45. Magnus Wrenninge and Nafees Bin Zafar. 2011. Production Volume Rendering. ACM SIGGRAPH Course notes. (July 2011).Google Scholar
    46. Cheng Yang, Xubo Yang, and Xiangyun Xiao. 2016. Data-driven projection method in fluid simulation. Computer Animation and Virtual Worlds 27, 3–4 (2016), 415–424.Google ScholarDigital Library
    47. Qizhi Yu, Fabrice Neyret, Eric Bruneton, and Nicolas Holzschuch. 2010. Lagrangian Texture Advection: Preserving both Spectrum and Velocity Field. IEEE Transactions on Visualization and Computer Graphics 17(11) (2010), 1612–1623.Google Scholar
    48. Sergey Zagoruyko and Nikos Komodakis. 2015. Learning to compare image patches via convolutional neural networks. In Proc. Computer Vision and Pattern Recognition. IEEE, 4353–4361. Google ScholarCross Ref
    49. Xinxin Zhang, Minchen Li, and Robert Bridson. 2016. Resolving Fluid Boundary Layers with Particle Strength Exchange and Weak Adaptivity. ACM Transactions on Graphics 35, 4 (2016), 76:1–76:8.Google ScholarDigital Library
    50. Yubo Zhang and Kwan-Liu Ma. 2013. Spatio-temporal Extrapolation for Fluid Animation. ACM Trans. Graph. 32, 6, Article 183 (Nov. 2013), 8 pages.Google ScholarDigital Library
    51. Bo Zhu, Xubo Yang, and Ye Fan. 2010. Creating and preserving vortical details in sph fluid. In Computer Graphics Forum, Vol. 29. Wiley Online Library, 2207–2214. Google ScholarCross Ref


ACM Digital Library Publication:



Overview Page: