ByeongSun Hong* Qimeng Zhang* Chang Hun Kim* Jung Lee** Jong-Hyun Kim***
(* : Korea University, ** : Hallym University, *** : Kangnam University)
IEEE Access 2021
Abstract : In this paper, we propose a highly efficient method for synthesizing smoke simulations with high resolution based on deep learning. A major issue for physics-based high-resolution 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 SR(Super-resolution) methods that convert LR(Lowresolution) 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, since the number of nodes increases when the resolution of the simulation space is large, we reduce the size of the space by multiscale 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 high-resolution 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.
[paper]