Transport-based neural style transfer for smoke simulations

Kim, Byungsoo; Azevedo, Vinícius; Groß, Markus; Solenthaler, Barbara

doi:10.1145/3355089.3356560

Cited by 40 publications

(26 citation statements)

References 57 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A novel generative model was also proposed to synthesize fluid simulations from a set of reduced parameters [44]. The first transport-based neural style transfer algorithm for volumetric smoke data was proposed to transfer features from natural images to smoke simulations [45]. Subsequently, an end-toend learning approach for the overall simulation process was proposed [46].…”

Section: B Fire Simulationmentioning

confidence: 99%

Learning Representation of Secondary Effects for Fire-Flake Animation

Choi

Kim³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

This paper proposes a new data-driven neural network-based fire-flake simulation model. Our model trains a neural network using precomputed fire simulation data. The trained neural network model generates fire flakes in appropriate locations and infers their velocity to make them appear natural to their surroundings. The neural network model consists of a fire-flake generator and a velocity modifier. The fireflake generator uses the velocity, temperature, and density fields of the precomputed fire simulation as inputs to determine the locations at which natural fire flakes would be generated. The velocity modifier takes the velocity field of the precomputed fire simulation as input and infers the velocity of the generated fire flakes so that they appear natural relative to the flame motions and surroundings. Our method adopts a neural network to efficiently improve the fire-flake simulation, enhancing the performance while maintaining the visual quality. Our model is approximately three times faster than the traditional fire-flake model. In particular, our model is 30 times faster in the velocity modification step. Our method is also easier to implement than the existing physically based fire-flake simulation method and can reduce the time spent by artists and developers on their applications.

show abstract

Section: B Fire Simulationmentioning

confidence: 99%

Learning Representation of Secondary Effects for Fire-Flake Animation

Choi

Kim³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Our method improves the efficiency in terms of speed and memory by applying the SR operation to the smoke simulation based on the adaptive grid (e.g., octree). Although our method does not represent realistic elements of the smoke movement, integrating our method into existing detail-enhancement studies can improve details and efficiency [5], [6], [51]. Some studies improve detail using deep learning for fluid simulation.…”

Section: ) 3d Scenesmentioning

confidence: 99%

“…B ECAUSE of advances in deep learning in recent years, physics-based simulation fields such as character animations [13], [14], [29] and fluid simulations [6], [15], [24], [30] have also been remarkably improved because of deep learning. Accuracy and efficiency in fields such as style transfer [5], [16], [27], character motion control [17], [26], and numerical analysis [18] have also improved.…”

Section: Introductionmentioning

confidence: 99%

Accelerated Smoke Simulation by Super-Resolution With Deep Learning on Downscaled and Binarized Space

et al. 2021

View full text Add to dashboard Cite

In this paper, we propose a highly efficient method for synthesizing high-resolution(HR) smoke simulations based on deep learning. A major issue for physics-based HR fluid simulations is that they require large amounts of physical memory and long execution times. In recent years, this issue has been addressed by developing deep-learning-based super-resolution(SR) methods that convert lowresolution(LR) fluid simulation results to HR(High-resolution) versions. However, these methods were not very efficient because they performed operations even in areas with low density or no density. In this paper, we propose a method that can maximize its efficiency by introducing a downscaled and binarized adaptive octree. However, even if it is divided by octree, because the number of nodes increases when the resolution of the simulation space is large, we reduce the size of the space by multiscaling and at the same time perform binarization to preserve the density that may be lost in this process. The octree calculated in this process has a structure similar to that of a multigrid solver, and the octree calculated at coarse resolution is restored to its original size and used for HR expression. Finally, we apply the SR process only to those areas having significant density values. Using the proposed method, the SR process is significantly faster and the memory efficiency is improved. The performance of our method is compared with that of an existing SR method to demonstrate its efficiency.

show abstract

“…Neural networks have also recently been applied to fluid simulations. Applications include prediction of the entire dynamics (Wiewel et al, 2019), reconstruction of simulations from a set of input parameters (Kim et al, 2019b), interactive shape design (Umetani and Bickel, 2018), inferring hidden physics quantities (Raissi et al, 2018), and artistic control for visual effects (Kim et al, 2019a). A comprehensive overview of machine learning for fluid dynamics can be found in Brunton et al (2020).…”

Section: Introductionmentioning

confidence: 99%

A Physics-Aware Neural Network Approach for Flow Data Reconstruction From Satellite Observations

et al. 2021

Self Cite

View full text Add to dashboard Cite

An accurate assessment of physical transport requires high-resolution and high-quality velocity information. In satellite-based wind retrievals, the accuracy is impaired due to noise while the maximal observable resolution is bounded by the sensors. The reconstruction of a continuous velocity field is important to assess transport characteristics and it is very challenging. A major difficulty is ambiguity, since the lack of visible clouds results in missing information and multiple velocity fields will explain the same sparse observations. It is, therefore, necessary to regularize the reconstruction, which would typically be done by hand-crafting priors on the smoothness of the signal or on the divergence of the resulting flow. However, the regularizers can smooth the solution excessively and will not guarantee that possible solutions are truly physically realizable. In this paper, we demonstrate that data recovery can be learned by a neural network from numerical simulations of physically realizable fluid flows, which can be seen as a data-driven regularization. We show that the learning-based reconstruction is especially powerful in handling large areas of missing or occluded data, outperforming traditional models for data recovery. We quantitatively evaluate our method on numerically-simulated flows, and additionally apply it to a Guadalupe Island case study—a real-world flow data set retrieved from satellite imagery of stratocumulus clouds.

show abstract

Transport-based neural style transfer for smoke simulations

Cited by 40 publications

References 57 publications

Learning Representation of Secondary Effects for Fire-Flake Animation

Learning Representation of Secondary Effects for Fire-Flake Animation

Accelerated Smoke Simulation by Super-Resolution With Deep Learning on Downscaled and Binarized Space

A Physics-Aware Neural Network Approach for Flow Data Reconstruction From Satellite Observations

Contact Info

Product

Resources

About