Abstract
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 low-resolution(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.
Highlights
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 been remarkably improved because of deep learning
In physics-based fluid simulation, it is an important issue that the amount of computation increases rapidly depending on the resolution, for 3D simulation
The existing deep learning methods for HR fluid simulation can be divided into two categories based on the type of application
Summary
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 been remarkably improved because of deep learning. Studies in the second category enhance the details of input LR simulation data by transforming the data into turbulent styles [43] or upscaling its resolution [12], [28] Both the style-transform and resolution-upscaling methods are applied to the entire simulation space including the low-density region, reducing the efficiency of the computation process. These approaches can produce HR smoke flow results from input LR smoke flows, they are inefficient because they perform operations on the entire space, including spaces where valid data do not exist To address this issue, we propose an accelerated SR method that partitions simulation data into regions with and without valid data based on a tree structure and performs the SR process only in regions with valid simulation data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
