Dynamic Upsampling of Smoke through Dictionary-based Learning

doi:doi.org/10.1145/3412360

	Dynamic Upsampling of Smoke through Dictionary-based Learning
	Bai, Kai1 ; Li, Wei1 ; Desbrun, Mathieu2 ; Liu, Xiaopei2
	2020-12-01
发表期刊	ACM TRANSACTIONS ON GRAPHICS (IF:7.8[JCR-2023],9.5[5-Year])
ISSN	0730-0301
EISSN	1557-7368
卷号	40 期号:1
发表状态	已发表
DOI	doi.org/10.1145/3412360
摘要	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 precomputed over-complete dictionary. These sparse coefficients are then used to generate a high-resolution smoke animation sequence by blending the fine counterparts of the coarse patches. Our network is initially trained from a sequence of example simulations to both construct the dictionary of corresponding coarse and fine patches and allow for the fast evaluation of a sparse patch encoding of any coarse input. The resulting network provides an accurate upsampling when the coarse input simulation is well approximated by patches present in the training set (e.g., for re-simulation), or simply visually plausible upsampling when input and training sets differ significantly. We show a variety of examples to ascertain the strengths and limitations of our approach and offer comparisons to existing approaches to demonstrate its quality and effectiveness. © 2020 ACM.
关键词	Blending Smoke Signal sampling Interactive computer graphics Fine resolution High resolution Learning approach Linear combinations Low resolution Over-complete dictionaries Smoke flows Training sets Fluid simulation Dictionary learning Neural networks Smoke animation dictionary learning neural networks smoke animation
URL	查看原文
收录类别	EI ; SCI ; SCIE
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000604780700004
出版者	Association for Computing Machinery
EI入藏号	20210109723318
EI主题词	Animation
EI分类号	723.2 Data Processing and Image Processing ; 723.5 Computer Applications ; 802.3 Chemical Operations ; 922 Statistical Methods
原始文献类型	Journal article (JA)
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/251734
专题	信息科学与技术学院_PI研究组_刘晓培组信息科学与技术学院信息科学与技术学院_博士生
作者单位	1.ShanghaiTech University/SIMIT/UCAS, Shanghai, China; 2.ShanghaiTech University, Shanghai, China
第一作者单位	上海科技大学
第一作者的第一单位	上海科技大学
推荐引用方式 GB/T 7714	Bai, Kai,Li, Wei,Desbrun, Mathieu,et al. Dynamic Upsampling of Smoke through Dictionary-based Learning[J]. ACM TRANSACTIONS ON GRAPHICS,2020,40(1).
APA	Bai, Kai,Li, Wei,Desbrun, Mathieu,&Liu, Xiaopei.(2020).Dynamic Upsampling of Smoke through Dictionary-based Learning.ACM TRANSACTIONS ON GRAPHICS,40(1).
MLA	Bai, Kai,et al."Dynamic Upsampling of Smoke through Dictionary-based Learning".ACM TRANSACTIONS ON GRAPHICS 40.1(2020).