tempoGAN
Authors:
- Erik FranzEFErik Franz
Top Cited Papers
Open Access
- 30 July 2018
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 37 (4) , 1-15
Abstract
We propose a temporally coherent generative model addressing the super-resolution problem for fluid flows. Our work represents a first approach to synthesize four-dimensional physics fields with neural networks. Based on a conditional generative adversarial network that is designed for the inference of three-dimensional volumetric data, our model generates consistent and detailed results by using a novel temporal discriminator, in addition to the commonly used spatial one. Our experiments show that the generator is able to infer more realistic high-resolution details by using additional physical quantities, such as low-resolution velocities or vorticities. Besides improvements in the training process and in the generated outputs, these inputs offer means for artistic control as well. We additionally employ a physics-aware data augmentation step, which is crucial to avoid overfitting and to reduce memory requirements. In this way, our network learns to generate adverted quantities with highly detailed, realistic, and temporally coherent features. Our method works instantaneously, using only a single time-step of low-resolution fluid data. We demonstrate the abilities of our method using a variety of complex inputs and applications in two and three dimensions.Keywords
Funding Information
- ERC
This publication has 23 references indexed in Scilit:
- Data-driven fluid simulations using regression forestsACM Transactions on Graphics, 2015
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Interactive localized liquid motion editingACM Transactions on Graphics, 2013
- Physics-inspired upsampling for cloth simulation in games2011
- Fast animation of turbulence using energy transport and procedural synthesisACM Transactions on Graphics, 2008
- Wavelet turbulence for fluid simulationACM Transactions on Graphics, 2008
- An Unconditionally Stable MacCormack MethodJournal of Scientific Computing, 2007
- Fluid control using the adjoint methodACM Transactions on Graphics, 2004
- Smoke simulation for large scale phenomenaACM Transactions on Graphics, 2003
- Stable fluids1999