Dynamic Upsampling of Smoke through Dictionary-based Learning
Bo K(柏凯); Li W(李伟); Mathieu Desbrun; Xiaopei Liu

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.

KeywordFluid simulation Dictionary learning Neural networks Smoke animation
Indexed BySCI
Document Type期刊论文
Corresponding AuthorXiaopei Liu
Recommended Citation
GB/T 7714
Kai Bai, Wei Li, Mathieu Desbrun, and Xiaopei Liu. 2020. Dynamic Upsampling of Smoke through Dictionary-based Learning. ACM Trans. Graph. 40, 1, Article 4 (September 2020), 19 pages. DOI:https://doi.org/10.1145/3412360
APA Bo K,Li W,Mathieu Desbrun,&Xiaopei Liu.(2020).Dynamic Upsampling of Smoke through Dictionary-based Learning.ACM TRANSACTIONS ON GRAPHICS.
MLA Bo K,et al."Dynamic Upsampling of Smoke through Dictionary-based Learning".ACM TRANSACTIONS ON GRAPHICS (2020).
Files in This Item: Download All
File Name/Size DocType Version Access License
doi.org@10.1145@3412(8826KB)期刊论文作者原稿开放获取UnknownView Download
Related Services
Usage statistics
Scholar Google
Similar articles in Scholar Google
[Bo K(柏凯)]'s Articles
[Li W(李伟)]'s Articles
[Mathieu Desbrun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Bo K(柏凯)]'s Articles
[Li W(李伟)]'s Articles
[Mathieu Desbrun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Bo K(柏凯)]'s Articles
[Li W(李伟)]'s Articles
[Mathieu Desbrun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: doi.org@10.1145@3412360.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.