DualSmoke: Sketch-based smoke illustration design with two-stage generative model  

作　　者：Haoran Xie Keisuke Arihara Syuhei Sato Kazunori Miyata 

机构地区：[1]Graduate School of Advanced Science and Technology,Japan Advanced Institute of Science and Technology,1-1 Nomi,Ishikawa 9231292,Japan [2]Graduate School of Computer and Information Sciences,Hosei University,3-7-2 Kajino-cho,Koganei-shi,Tokyo 1848584,Japan

出　　处：《Computational Visual Media》2024年第5期965-979,共15页计算可视媒体（英文版）

基　　金：supported by a JAIST Research Grant,and JSPS KAKENHI grant JP20K19845.

摘　　要：The dynamic effects of smoke are impressive in illustration design,but it is a troublesome and challenging issue for inexpert users to design smoke effects without domain knowledge of fuid simulations.In this work,we propose DualSmoke,a two-stage globalto-local generation framework for interactive smoke illustration design.In the global stage,the proposed approach utilizes fluid patterns to generate Lagrangian coherent structures from the user's hand-drawn sketches.In the local stage,detailed flow patterns are obtained from the generated coherent structure.Finally,we apply a guiding force field to the smoke simulator to produce the desired smoke illustration.To construct the training dataset,DualSmoke generates flow patterns using finite-time Lyapunov exponents of the velocity fields.The synthetic sketch data are generated from the fow patterns by skeleton extraction.Our user study verifies that the proposed design interface can provide various smoke illustration designs with good user usability.Our code is available at https://github.com/shasph/DualSmoke.

关 键 词：smoke simulation flow control generative adversarial network(GAN) finite-time lyapunov exponent(FTLE) Lagrangian coherent structure(LCS) 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]