Abstract
Artistically controlling fluids has always been a challenging task. Recently, volumetric Neural Style Transfer (NST) techniques have been used to artistically manipulate smoke simulation data with 2D images. In this work, we revisit previous volumetric NST techniques for smoke, proposing a suite of upgrades that enable stylizations that are significantly faster, simpler, more controllable and less prone to artifacts. Moreover, the energy minimization solved by previous methods is camera dependent. To avoid that, a computationally expensive iterative optimization performed for multiple views sampled around the original simulation is needed, which can take up to several minutes per frame. We propose a simple feed-forward neural network architecture that is able to infer view-independent stylizations that are three orders of the magnitude faster than its optimization-based counterpart.
- Kai Bai, Wei Li, Mathieu Desbrun, and Xiaopei Liu. 2019. Dynamic Upsampling of Smoke through Dictionary-based Learning. (oct 2019). arXiv:1910.09166 http://arxiv.org/abs/1910.09166Google Scholar
- Kai Bai, Chunhao Wang, Mathieu Desbrun, and Xiaopei Liu. 2021. Predicting high-resolution turbulence details in space and time. ACM Transactions on Graphics 40, 6 (dec 2021), 1--16. Google ScholarDigital Library
- Mengyu Chu and Nils Thuerey. 2017. Data-driven synthesis of smoke flows with CNN-based feature descriptors. ACM Transactions on Graphics 36, 4 (jul 2017), 1--14. Google ScholarDigital Library
- Mengyu Chu, Nils Thuerey, Hans-Peter Seidel, Christian Theobalt, and Rhaleb Zayer. 2021. Learning meaningful controls for fluids. ACM Transactions on Graphics 40, 4 (aug 2021), 1--13. Google ScholarDigital Library
- Graham Collier. 2022. Raya and the Last Dragon. https://www.sidefx.com/community/raya-and-the-last-dragon/Google Scholar
- Vincent Dumoulin, Jonathon Shlens, and Manjunath Kudlur. 2017. A Learned Representation For Artistic Style. ICLR (2017). https://arxiv.org/abs/1610.07629Google Scholar
- Julian Fong, Magnus Wrenninge, Christopher Kulla, and Ralf Habel. 2017. Production volume rendering. In ACM SIGGRAPH 2017 Courses on - SIGGRAPH '17. ACM Press, New York, New York, USA, 1--79. Google ScholarDigital Library
- Erik Franz, Barbara Solenthaler, and Nils Thuerey. 2021. Global Transport for Fluid Reconstruction with Learned Self-Supervision. (apr 2021). arXiv:2104.06031 http://arxiv.org/abs/2104.06031Google Scholar
- Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. 2016. Image Style Transfer Using Convolutional Neural Networks. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2414--2423. Google ScholarCross Ref
- Jie Guo, Mengtian Li, Zijing Zong, Yuntao Liu, Jingwu He, Yanwen Guo, and Ling Qi Yan. 2021. Volumetric appearance stylization with stylizing kernel prediction network. ACM Transactions on Graphics (TOG) 40, 4 (jul 2021). Google ScholarDigital Library
- Jun Han and Chaoli Wang. 2022. TSR-VFD: Generating temporal super-resolution for unsteady vector field data. Computers Graphics 103 (apr 2022), 168--179. Google ScholarDigital Library
- Philipp Holl, Nils Thuerey, and Vladlen Koltun. 2020. Learning to Control PDEs with Differentiable Physics. In International Conference on Learning Representations.Google Scholar
- Yuanming Hu, Jiancheng Liu, Andrew Spielberg, Joshua B. Tenenbaum, William T. Freeman, Jiajun Wu, Daniela Rus, and Wojciech Matusik. 2018. ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics. (oct 2018). arXiv:1810.01054 http://arxiv.org/abs/1810.01054Google Scholar
- Yuanming Hu, Xinxin Zhang, Ming Gao, and Chenfanfu Jiang. 2019. On hybrid lagrangian-eulerian simulation methods: practical notes and high-performance aspects. In ACM SIGGRAPH 2019 Courses. ACM, 16.Google ScholarDigital Library
- Yongcheng Jing, Yang Liu, Yezhou Yang, Zunlei Feng, Yizhou Yu, Dacheng Tao, and Mingli Song. 2018. Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields. 244--260. Google ScholarDigital Library
- Yongcheng Jing, Yezhou Yang, Zunlei Feng, Jingwen Ye, Yizhou Yu, and Mingli Song. 2019. Neural Style Transfer: A Review. IEEE Transactions on Visualization and Computer Graphics (2019), 1--1. Google ScholarCross Ref
- Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual losses for real-time style transfer and super-resolution. In European Conference on Computer Vision.Google ScholarCross Ref
- Hiroharu Kato, Yoshitaka Ushiku, and Tatsuya Harada. 2018. Neural 3d mesh renderer. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3907--3916.Google ScholarCross Ref
- Byungsoo Kim, Vinicius C. Azevedo, Markus Gross, and Barbara Solenthaler. 2019a. Transport-based neural style transfer for smoke simulations. ACM Transactions on Graphics 38, 6 (dec 2019), 1--11. Google ScholarDigital Library
- Byungsoo Kim, Vinicius C. Azevedo, Markus Gross, and Barbara Solenthaler. 2020. Lagrangian neural style transfer for fluids. ACM Transactions on Graphics 39, 4 (aug 2020). Google ScholarDigital Library
- Byungsoo Kim, Vinicius C. Azevedo, Nils Thuerey, Theodore Kim, Markus Gross, and Barbara Solenthaler. 2019b. Deep Fluids: A Generative Network for Parameterized Fluid Simulations. Computer Graphics Forum (Proc. Eurographics) 38, 2 (2019).Google Scholar
- Byungsoo Kim, Xingchang Huang, Laura Wuelfroth, Jingwei Tang, Guillaume Cordonnier, Markus Gross, and Barbara Solenthaler. 2022. Deep Reconstruction of 3D Smoke Densities from Artist Sketches. Computer Graphics Forum (Proc. Eurographics) 41, 2 (2022).Google Scholar
- Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. Google ScholarCross Ref
- M. Kohlbrenner, U. Finnendahl, T. Djuren, and M. Alexa. 2021. Gauss Stylization: Interactive Artistic Mesh Modeling based on Preferred Surface Normals. Computer Graphics Forum 40, 5 (aug 2021), 33--43. Google ScholarCross Ref
- L'ubor Ladický, SoHyeon Jeong, Barbara Solenthaler, Marc Pollefeys, and Markus Gross. 2015. Data-driven fluid simulations using regression forests. ACM Transactions on Graphics 34, 6 (oct 2015), 1--9. Google ScholarDigital Library
- Shaohua Li, Xinxing Xu, Liqiang Nie, and Tat-Seng Chua. 2017b. Laplacian-Steered Neural Style Transfer. In Proceedings of the 2017 ACM on Multimedia Conference - MM '17. ACM Press, New York, New York, USA, 1716--1724. Google ScholarDigital Library
- Xueting Li, Sifei Liu, Jan Kautz, and Ming-Hsuan Yang. 2019. Learning Linear Transformations for Fast Image and Video Style Transfer. In IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
- Yanghao Li, Naiyan Wang, Jiaying Liu, and Xiaodi Hou. 2017a. Demystifying Neural Style Transfer. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI'17). AAAI Press, 2230--2236.Google ScholarCross Ref
- Zijie Li and Amir Barati Farimani. 2022. Graph neural network-accelerated Lagrangian fluid simulation. Computers Graphics 103 (apr 2022), 201--211. Google ScholarDigital Library
- Hsueh-Ti Derek Liu and Alec Jacobson. 2019. Cubic Stylization. (oct 2019). arXiv:1910.02926 Google ScholarDigital Library
- Hsueh-Ti Derek Liu, Michael Tao, and Alec Jacobson. 2018. Paparazzi: Surface Editing by way of Multi-View Image Processing. ACM Transactions on Graphics (2018).Google Scholar
- Fujun Luan, Sylvain Paris, Eli Shechtman, and Kavita Bala. 2017. Deep Photo Style Transfer. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 6997--7005. Google ScholarCross Ref
- Oscar Michel, Roi Bar-On, Richard Liu, Sagie Benaim, and Rana Hanocka. 2021. Text2Mesh: Text-Driven Neural Stylization for Meshes. (dec 2021). arXiv:2112.03221 http://arxiv.org/abs/2112.03221Google Scholar
- Mike Navarro and Jacob Rice. 2021. Stylizing Volumes with Neural Networks. In ACM SIGGRAPH 2021 Talks. ACM, New York, NY, USA, 1--2. Google ScholarDigital Library
- Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. Google ScholarCross Ref
- Eric Risser, Pierre Wilmot, and Connelly Barnes. 2017. Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses. (jan 2017). arXiv:1701.08893 http://arxiv.org/abs/1701.08893Google Scholar
- Manuel Ruder, Alexey Dosovitskiy, and Thomas Brox. 2018. Artistic Style Transfer for Videos and Spherical Images. International Journal of Computer Vision 126, 11 (nov 2018), 1199--1219. Google ScholarDigital Library
- Connor Schenck and Dieter Fox. 2018. SPNets: Differentiable Fluid Dynamics for Deep Neural Networks. (jun 2018). arXiv:1806.06094 http://arxiv.org/abs/1806.06094Google Scholar
- Ahmed Selim, Mohamed Elgharib, and Linda Doyle. 2016. Painting style transfer for head portraits using convolutional neural networks. ACM Transactions on Graphics 35, 4 (jul 2016), 1--18. Google ScholarDigital Library
- Andrew Selle, Ronald Fedkiw, ByungMoon Kim, Yingjie Liu, and Jarek Rossignac. 2008. An Unconditionally Stable MacCormack Method. Journal of Scientific Computing 35, 2--3 (jun 2008), 350--371. Google ScholarDigital Library
- Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. (sep 2014). arXiv:1409.1556 http://arxiv.org/abs/1409.1556Google Scholar
- Leslie N. Smith and Nicholay Topin. 2017. Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates. Google ScholarCross Ref
- Steven W Smith. 1997. The Scientist and Engineer's Guide to Digital Signal Processing. California Technical Publishing, USA.Google ScholarDigital Library
- Jingwei Tang, Vinicius C. Azevedo, Guillaume Cordonnier, and Barbara Solenthaler. 2021. Honey, I Shrunk the Domain: Frequency-aware Force Field Reduction for Efficient Fluids Optimization. Computer Graphics Forum 40, 2 (may 2021), 339--353. Google ScholarCross Ref
- Nils Thuerey, Philipp Holl, Maximilian Mueller, Patrick Schnell, Felix Trost, and Kiwon Um. 2021. Physics-based Deep Learning. (sep 2021). arXiv:2109.05237 http://arxiv.org/abs/2109.05237Google Scholar
- Nils Thuerey and Tobias Pfaff. 2018. MantaFlow. http://mantaflow.com.Google Scholar
- Jonathan Tompson, Kristofer Schlachter, Pablo Sprechmann, and Ken Perlin. 2016. Accelerating Eulerian Fluid Simulation With Convolutional Networks. (jul 2016). arXiv:1607.03597 http://arxiv.org/abs/1607.03597Google Scholar
- Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2016. Instance Normalization: The Missing Ingredient for Fast Stylization. (jul 2016). arXiv:1607.08022 http://arxiv.org/abs/1607.08022Google Scholar
- Kiwon Um, Robert Brand, Yun, Fei, Philipp Holl, and Nils Thuerey. 2020. Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers. (jun 2020). arXiv:2007.00016 http://arxiv.org/abs/2007.00016Google Scholar
- Nobuyuki Umetani and Bernd Bickel. 2018. Learning three-dimensional flow for interactive aerodynamic design. ACM Transactions on Graphics 37, 4 (jul 2018), 1--10. Google ScholarDigital Library
- Xin Wang, Geoffrey Oxholm, Da Zhang, and Yuan-Fang Wang. 2016. Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer. (nov 2016). arXiv:1612.01895 http://arxiv.org/abs/1612.01895Google Scholar
- You Xie, Erik Franz, Mengyu Chu, and Nils Thuerey. 2018. tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow. arXiv preprint arXiv:1801.09710 (jan 2018). arXiv:1801.09710 http://arxiv.org/abs/1801.09710Google Scholar
- Guowei Yan, Zhili Chen, Jimei Yang, and Huamin Wang. 2020. Interactive liquid splash modeling by user sketches. ACM Transactions on Graphics 39, 6 (dec 2020), 1--13. Google ScholarDigital Library
- Cheng Yang, Xubo Yang, and Xiangyun Xiao. 2016. Data-driven projection method in fluid simulation. Computer Animation and Virtual Worlds 27, 3--4 (may 2016), 415--424. Google ScholarDigital Library
- Kangxue Yin, Jun Gao, Maria Shugrina, Sameh Khamis, and Sanja Fidler. 2021. 3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations. (aug 2021). arXiv:2108.12958 http://arxiv.org/abs/2108.12958Google Scholar
- Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. 2017. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, 2242--2251. Google ScholarCross Ref
Index Terms
- Efficient Neural Style Transfer for Volumetric Simulations
Recommendations
Neural style transfer: a paradigm shift for image-based artistic rendering?
NPAR '17: Proceedings of the Symposium on Non-Photorealistic Animation and RenderingIn this meta paper we discuss image-based artistic rendering (IB-AR) based on neural style transfer (NST) and argue, while NST may represent a paradigm shift for IB-AR, that it also has to evolve as an interactive tool that considers the design aspects ...
Model Renderer Design with Style Image
AIAM2020: Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced ManufactureA model renderer with style image generation is designed combine with illumination technology and style transfer technology for the illumination problems, that may be encountered in the process of computer image graphics design and production.In order ...
Efficient Neural Networks for Real-time Motion Style Transfer
Style is an intrinsic, inescapable part of human motion. It complements the content of motion to convey meaning, mood, and personality. Existing state-of-the-art motion style methods require large quantities of example data and intensive computational ...
Comments