{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T19:17:59Z","timestamp":1762543079470,"version":"3.40.5"},"reference-count":45,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2019,6,7]],"date-time":"2019-06-07T00:00:00Z","timestamp":1559865600000},"content-version":"vor","delay-in-days":37,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"published-print":{"date-parts":[[2019,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Eulerian\u2010based smoke simulations are sensitive to the initial parameters and grid resolutions. Due to the numerical dissipation on different levels of the grid and the nonlinearity of the governing equations, the differences in simulation resolutions will result in different results. This makes it challenging for artists to preview the animation results based on low\u2010resolution simulations. In this paper, we propose a learning\u2010based flow correction method for fast previewing based on low\u2010resolution smoke simulations. The main components of our approach lie in a deep convolutional neural network, a grid\u2010layer feature vector and a special loss function. We provide a novel matching model to represent the relationship between low\u2010resolution and high\u2010resolution smoke simulations and correct the overall shape of a low\u2010resolution simulation to closely follow the shape of a high\u2010resolution down\u2010sampled version. We introduce the grid\u2010layer concept to effectively represent the 3D fluid shape, which can also reduce the input and output dimensions. We design a special loss function for the fluid divergence\u2010free constraint in the neural network training process. We have demonstrated the efficacy and the generality of our approach by simulating a diversity of animations deviating from the original training set. In addition, we have integrated our approach into an existing fluid simulation framework to showcase its wide applications.<\/jats:p>","DOI":"10.1111\/cgf.13649","type":"journal-article","created":{"date-parts":[[2019,6,7]],"date-time":"2019-06-07T14:34:52Z","timestamp":1559918092000},"page":"431-440","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["A CNN\u2010based Flow Correction Method for Fast Preview"],"prefix":"10.1111","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7304-220X","authenticated-orcid":false,"given":"Xiangyun","family":"Xiao","sequence":"first","affiliation":[{"name":"Digital ART Lab, School of Software Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Digital ART Lab, School of Software Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xubo","family":"Yang","sequence":"additional","affiliation":[{"name":"Digital ART Lab, School of Software Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2019,6,7]]},"reference":[{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882364"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276435"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1201\/b10635"},{"key":"e_1_2_9_5_2","unstructured":"CaballeroJ. LedigC. AitkenA. AcostaA. TotzJ. WangZ. ShiW.:Real\u2010time video super\u2010resolution with spatiotemporal networks and motion compensation. 2848\u20132857. URL:doi.ieeecomputersociety.org\/10.1109\/CVPR.2017.304. 2 5"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073643"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"FedkiwR. StamJ. JensenH. W.: Visual simulation of smoke. InProceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques(2001) ACM pp.15\u201322. 1","DOI":"10.1145\/383259.383260"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-013-0798-0"},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03228.x"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"HuangR. MelekZ. KeyserJ.: Preview\u2010based sampling for controlling gaseous simulations. InACM Siggraph\/eurographics Symposium on Computer Animation(2011) pp.177\u2013186. 1 2","DOI":"10.1145\/2019406.2019430"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.1761178"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1002\/cav.408"},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2766983"},{"issue":"6","key":"e_1_2_9_16_2","first-page":"199","article-title":"Data\u2010driven fluid simulations using regression forests","volume":"34","author":"Jeong S.","year":"2015","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2714572"},{"key":"e_1_2_9_18_2","unstructured":"KingmaD. P. BaJ.: Adam: A Method for Stochastic Optimization.ArXiv e\u2010prints(Dec.2014). URL:http:\/\/adsabs.harvard.edu\/abs\/2014arXiv1412.6980K arXiv:1412.6980. 6"},{"key":"e_1_2_9_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360649"},{"key":"e_1_2_9_20_2","unstructured":"KrizhevskyA. SutskeverI. HintonG. E.: Imagenet classification with deep convolutional neural networks. InInternational Conference on Neural Information Processing Systems(2012) pp.1097\u20131105. 2"},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01640.x"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"NielsenM. B. ChristensenB. B. ZafarN. B. RobleD. MusethK.: Guiding of smoke animations through variational coupling of simulations at different resolutions. InACM Siggraph\/eurographics Symposium on Computer Animation SCA 2009 New Orleans Louisiana Usa August(2009) pp.217\u2013226. 1 2 3","DOI":"10.1145\/1599470.1599499"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/1409060.1409119"},{"key":"e_1_2_9_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508429"},{"key":"e_1_2_9_25_2","unstructured":"PanZ. ManochaD.: Efficient optimal control of smoke using spacetime multigrid.arXiv preprint arXiv:1608.01102(2016). URL:http:\/\/arxiv.org\/abs\/1608.01102. 2"},{"key":"e_1_2_9_26_2","doi-asserted-by":"crossref","unstructured":"PanZ. ManochaD.: Motion planning for fluid manipulation using simplified dynamics. InIntelligent Robots and Systems (IROS) 2016 IEEE\/RSJ International Conference on(2016) IEEE pp.4224\u20134231. URL:http:\/\/doi.acm.org\/10.1109\/IROS.2016.7759622. 2 3","DOI":"10.1109\/IROS.2016.7759622"},{"key":"e_1_2_9_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3016963"},{"key":"e_1_2_9_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/1882261.1866196"},{"key":"e_1_2_9_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618467"},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882335"},{"key":"e_1_2_9_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601126"},{"key":"e_1_2_9_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201398"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"StamJ. FiumeE.: Depicting fire and other gaseous phenomena using diffusion processes. InConference on Computer Graphics and Interactive Techniques(1995) pp.129\u2013136. 2","DOI":"10.1145\/218380.218430"},{"key":"e_1_2_9_34_2","doi-asserted-by":"crossref","unstructured":"SatoS. MoritaT. DobashiY. YamamotoT.: A data\u2010driven approach for synthesizing high\u2010resolution animation of fire. InProceedings of the digital production symposium(2012) ACM pp.37\u201342. 3","DOI":"10.1145\/2370919.2370926"},{"key":"e_1_2_9_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980253"},{"key":"e_1_2_9_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/2956233"},{"key":"e_1_2_9_37_2","unstructured":"TompsonJ. SchlachterK. SprechmannP. PerlinK.: Accelerating eulerian fluid simulation with convolutional networks.arXiv preprint arXiv:1607.03597(2016).2 3"},{"key":"e_1_2_9_38_2","unstructured":"UmK. HuX. ThuereyN.: Liquid splash modeling with neural networks.arXiv preprint arXiv: 1704.04456(2017).3"},{"key":"e_1_2_9_39_2","unstructured":"WangF. KangL. LiY.: Sketch\u2010based 3d shape retrieval using convolutional neural networks. In2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR) (June2015) Vol. 00 pp.1875\u20131883. URL:doi.ieeecomputersociety.org\/10.1109\/CVPR.2015. 7298797 doi:10.1109\/CVPR.2015. 7298797. 2 5"},{"key":"e_1_2_9_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201304"},{"key":"e_1_2_9_41_2","doi-asserted-by":"publisher","DOI":"10.1002\/cav.1837"},{"key":"e_1_2_9_42_2","doi-asserted-by":"crossref","unstructured":"YuanZ. ChenF. ZhaoY.: Pattern\u2010guided smoke animation with lagrangian coherent structure. InSIGGRAPH Asia Conference(2011) p.136. 1","DOI":"10.1145\/2024156.2024170"},{"key":"e_1_2_9_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2013.05.001"},{"key":"e_1_2_9_44_2","doi-asserted-by":"publisher","DOI":"10.1002\/cav.1695"},{"key":"e_1_2_9_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201324"},{"key":"e_1_2_9_46_2","unstructured":"ZhaoY. YuanZ. ChenF.: Enhancing fluid animation with adaptive controllable and intermittent turbulence. InEurographics\/acm SIGGRAPH Symposium on Computer Animation SCA 2010 Madrid Spain(2010) pp.75\u201384. 1 2"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Fcgf.13649","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.13649","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.13649","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.13649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T01:58:40Z","timestamp":1693360720000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.13649"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,5]]}},"alternative-id":["10.1111\/cgf.13649"],"URL":"https:\/\/doi.org\/10.1111\/cgf.13649","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"type":"print","value":"0167-7055"},{"type":"electronic","value":"1467-8659"}],"subject":[],"published":{"date-parts":[[2019,5]]},"assertion":[{"value":"2019-06-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}