A Dimension‐reduced Pressure Solver for Liquid Simulations

Ando, Ryoichi; Thürey, Nils; Wojtan, Chris

doi:10.1111/cgf.12576

Cited by 26 publications

(21 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach was later extended [KD13] with a cubature approach for enabling semi‐Lagrangian and MacCormack [SFK*08] advection schemes, while improving the handling of boundary conditions. Reduced‐order modelling was also explored to accelerate the pressure projection step in liquid simulations [ATW15].…”

Section: Related Work and Backgroundmentioning

confidence: 99%

Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow

Wiewel

Kim

Azevedo

et al. 2020

Computer Graphics Forum

View full text Add to dashboard Cite

We propose an end‐to‐end trained neural network architecture to robustly predict the complex dynamics of fluid flows with high temporal stability. We focus on single‐phase smoke simulations in 2D and 3D based on the incompressible Navier‐Stokes (NS) equations, which are relevant for a wide range of practical problems. To achieve stable predictions for long‐term flow sequences with linear execution times, a convolutional neural network (CNN) is trained for spatial compression in combination with a temporal prediction network that consists of stacked Long Short‐Term Memory (LSTM) layers. Our core contribution is a novel latent space subdivision (LSS) to separate the respective input quantities into individual parts of the encoded latent space domain. As a result, this allows to distinctively alter the encoded quantities without interfering with the remaining latent space values and hence maximizes external control. By selectively overwriting parts of the predicted latent space points, our proposed method is capable to robustly predict long‐term sequences of complex physics problems, like the flow of fluids. In addition, we highlight the benefits of a recurrent training on the latent space creation, which is performed by the spatial compression network. Furthermore, we thoroughly evaluate and discuss several different components of our method.

show abstract

Section: Related Work and Backgroundmentioning

confidence: 99%

Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow

Wiewel

Kim

Azevedo

et al. 2020

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…These simulations have a long history in Graphics [Kass and Miller 1990], but especially for larger resolutions, computing a pressure eld to make the ow divergence-free can become a bottleneck. Di erent methods to speed up the necessary calculations have been proposed, e.g., multi-grid solvers [McAdams et al 2010], coarse projections [Lentine et al 2010], or lower-dimensional approximations [Ando et al 2015]. Another crucial part of Eulerian solvers is computing the transport in the grid.…”

Section: Related Workmentioning

confidence: 99%

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

2017

View full text Add to dashboard Cite

Deformation-limiting advection Descriptor learning CNN CNN Fig. 1. We enable volumetric fluid synthesis with high resolutions and non-dissipative small scale details using CNNs and a fluid flow repository.We present a novel data-driven algorithm to synthesize high resolution ow simulations with reusable repositories of space-time ow data. In our work, we employ a descriptor learning approach to encode the similarity between uid regions with di erences in resolution and numerical viscosity. We use convolutional neural networks to generate the descriptors from uid data such as smoke density and ow velocity. At the same time, we present a deformation limiting patch advection method which allows us to robustly track deformable uid regions. With the help of this patch advection, we generate stable space-time data sets from detailed uids 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 e cient, and resolution independent. We will demonstrate with several examples that our method yields volumes with very high e ective resolutions, and non-dissipative small scale details that naturally integrate into the motions of the underlying ow.

show abstract

“…Composite grid‐based methods focused on data structure and tried to decrease computing resource to allocate in the regions of no interest. Model and dimension reduction methods are also used to speed up pressure projection step by dimension reduction technologies.…”

Section: Related Workmentioning

confidence: 99%

Adaptive learning‐based projection method for smoke simulation

Xiao

Yang

2018

Computer Animation & Virtual

View full text Add to dashboard Cite

Traditional Eulerian-based fluid simulations require much time and computational resources to solve the projection step, especially the large linear system produced by the Poisson equation. In this paper, we propose an adaptive machine-learning-based projection method combining deep neural network and incremental learning technique. We provide two modes: Fast Mode and Normal Mode to solve the most time-consuming projection step and deal with various simulation scenes largely different from the training data set. We introduce patch-based feature vectors to represent the whole velocity field and a loss function to keep the divergence-free constraint. We have demonstrated the acceleration and extrapolation ability of our method by testing various smoke scenes far different from our training data set. KEYWORDS deep neural network, fluid simulation, incremental learning Comput Anim Virtual Worlds. 2018;29:e1837.wileyonlinelibrary.com/journal/cav

show abstract

A Dimension‐reduced Pressure Solver for Liquid Simulations

Cited by 26 publications

References 25 publications

Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow

Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow

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

Adaptive learning‐based projection method for smoke simulation

Contact Info

Product

Resources

About