Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published September 2020 | Submitted + Published
Journal Article Open

Dynamic Upsampling of Smoke through Dictionary-based Learning

Abstract

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.

Additional Information

© 2020 Association for Computing Machinery. Received October 2019; revised July 2020; accepted July 2020. This work was supported by the Young Scientists Fund of the National Natural Science Foundation of China (Grant No. 61502305) and a startup funding from ShanghaiTech University.

Attached Files

Published - 3412360.pdf

Submitted - 1910.09166.pdf

Files

1910.09166.pdf
Files (20.5 MB)
Name Size Download all
md5:56f78e58cae7a97344023fd49189897e
9.0 MB Preview Download
md5:d9b5998b233e56a581f14d0a0f4b59ca
11.5 MB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 23, 2023