Dynamic Upsampling of Smoke through Dictionary-based Learning

  title={Dynamic Upsampling of Smoke through Dictionary-based Learning},
  author={Kai-Yi Bai and Wei Li and Mathieu Desbrun and Xiaopei Liu},
  journal={ACM Transactions on Graphics (TOG)},
  pages={1 - 19}
Simulating turbulent smoke flows with fine details is computationally intensive. For iterative editing or simply faster generation, efficiently upsampling a low-resolution numerical simulation is an attractive alternative. We propose a novel learning approach to the dynamic upsampling of smoke flows based on a training set of flows at coarse and fine resolutions. Our multiscale neural network turns an input coarse animation into a sparse linear combination of small velocity patches present in a… Expand
Two‐step Temporal Interpolation Network Using Forward Advection for Efficient Smoke Simulation
  • Young-Jin Oh, In-Kwon Lee
  • Computer Science
  • Comput. Graph. Forum
  • 2021
The proposed two‐step temporal interpolation network using forward advection to generate smoke simulation efficiently is found to be more accurate and closer to the ground truth smoke simulation than those generated by the previous temporal interpolations. Expand
Frequency-domain smoke guiding
We propose a simple and efficient method for guiding an Eulerian smoke simulation to match the behavior of a specified velocity field, such as a low-resolution animation of the same scene, whileExpand
Deep Learning-based Upscaling for In Situ Volume Visualization
Complementary to the classical use of feature-based condensation and temporal subsampling for in situ visualization, learning-based data upscaling has recently emerged as an interesting approach thatExpand
Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
High-resolution (HR) information of fluid flows, although preferable, is usually less accessible due to limited computational or experimental resources. In many cases, fluid data are generallyExpand
GPU Optimization for High-Quality Kinetic Fluid Simulation
This paper presents multiple novel GPU optimization techniques to efficiently implement high-quality ACM-MRT-based kinetic fluid simulations in domains containing complex solids, and extended the method to multi-GPU systems to enable large-scale simulations. Expand
Physics-Informed Super-Resolution for Real-Time Prediction of Urban Micrometeorology
The present paper proposes a physics-informed super-resolution (SR) model based on a convolutional neural network and applies it to the near-surface temperature in urban areas with the scaling factorExpand


Data-driven synthesis of smoke flows with CNN-based feature descriptors
This work employs a descriptor learning approach to encode the similarity between fluid regions with differences in resolution and numerical viscosity, and uses convolutional neural networks to generate the descriptors from fluid data such as smoke density and flow velocity. Expand
Example-based turbulence style transfer
This paper shows that style transfer methods from image editing can be adapted to transfer the turbulent style of an existing fluid simulation onto a new one by extending example-based image synthesis methods to handle velocity fields using a combination of patch-based and optimization-based texture synthesis. Expand
Physics-inspired upsampling for cloth simulation in games
We propose a method for learning linear upsampling operators for physically-based cloth simulation, allowing us to enrich coarse meshes with mid-scale details in minimal time and memory budgets, asExpand
Physics-inspired upsampling for cloth simulation in games
We propose a method for learning linear upsampling operators for physically-based cloth simulation, allowing us to enrich coarse meshes with mid-scale details in minimal time and memory budgets, asExpand
Data-driven fluid simulations using regression forests
This paper proposes a novel machine learning based approach, that formulates physics-based fluid simulation as a regression problem, estimating the acceleration of every particle for each frame, and designed a feature vector, directly modelling individual forces and constraints from the Navier-Stokes equations. Expand
Deep Fluids: A Generative Network for Parameterized Fluid Simulations
The proposed generative model is optimized for fluids by a novel loss function that guarantees divergence‐free velocity fields at all times, thus enabling applications such as fast construction of simulations, interpolation of fluids with different parameters, time re‐sampling, latent space simulations, and compression of fluid simulation data. Expand
Accelerating Eulerian Fluid Simulation With Convolutional Networks
This work proposes a data-driven approach that leverages the approximation power of deep-learning with the precision of standard solvers to obtain fast and highly realistic simulations of the Navier-Stokes equations. Expand
tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow
This 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, and generates consistent and detailed results. Expand
SPGrid: a sparse paged grid structure applied to adaptive smoke simulation
A new method for fluid simulation on high-resolution adaptive grids which rivals the throughput and parallelism potential of methods based on uniform grids is introduced and an adaptive multigrid-preconditioned Conjugate Gradient solver is demonstrated that achieves resolution-independent convergence rates while admitting a lightweight implementation with a modest memory footprint. Expand
Simulating water and smoke with an octree data structure
A new technique for discretizing the Poisson equation on this octree grid is proposed enabling the use of fast solution methods such as preconditioned conjugate gradients and results in a non-symmetric linear system which is more computationally challenging to invert. Expand