{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T15:53:34Z","timestamp":1771862014348,"version":"3.50.1"},"reference-count":75,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T00:00:00Z","timestamp":1600387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61502305"],"award-info":[{"award-number":["61502305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2021,2,28]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1145\/3412360","type":"journal-article","created":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T16:15:44Z","timestamp":1600445744000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Dynamic Upsampling of Smoke through Dictionary-based Learning"],"prefix":"10.1145","volume":"40","author":[{"given":"Kai","family":"Bai","sequence":"first","affiliation":[{"name":"ShanghaiTech University\/SIMIT\/UCAS, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"ShanghaiTech University\/SIMIT\/UCAS, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathieu","family":"Desbrun","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopei","family":"Liu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,9,18]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Proceedings of the Operating Systems Design and Implementation Conference","volume":"16","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi , Paul Barham , Jianmin Chen , Zhifeng Chen , Andy Davis , Jeffrey Dean , Matthieu Devin , Sanjay Ghemawat , Geoffrey Irving , Michael Isard , et\u00a0al. 2016 . Tensorflow: A system for large-scale machine learning . In Proceedings of the Operating Systems Design and Implementation Conference , Vol. 16 . 265--283. Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et\u00a0al. 2016. Tensorflow: A system for large-scale machine learning. In Proceedings of the Operating Systems Design and Implementation Conference, Vol. 16. 265--283."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185558"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461982"},{"key":"e_1_2_2_5_1","volume-title":"Proceedings of the Symposium on Computer Animation. 209--217","author":"Becker Markus","year":"2007","unstructured":"Markus Becker and Matthias Teschner . 2007 . Weakly compressible SPH for free surface flows . In Proceedings of the Symposium on Computer Animation. 209--217 . Markus Becker and Matthias Teschner. 2007. Weakly compressible SPH for free surface flows. In Proceedings of the Symposium on Computer Animation. 209--217."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2708040"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276435"},{"key":"e_1_2_2_8_1","volume-title":"Proceedings of the Symposium on Computer Animation. 87--95","author":"Brochu Tyson","year":"2012","unstructured":"Tyson Brochu , Todd Keeler , and Robert Bridson . 2012 . Linear-time smoke animation with vortex sheet meshes . In Proceedings of the Symposium on Computer Animation. 87--95 . Tyson Brochu, Todd Keeler, and Robert Bridson. 2012. Linear-time smoke animation with vortex sheet meshes. In Proceedings of the Symposium on Computer Animation. 87--95."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.fluid.30.1.329"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925868"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073643"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20042"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766901"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.95.013310"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-7486-9_5"},{"key":"e_1_2_2_16_1","article-title":"Multiple--relaxation--time lattice Boltzmann models in three dimensions","volume":"360","author":"Humi\u00e8res Dominique","year":"2002","unstructured":"Dominique d\u2019 Humi\u00e8res . 2002 . Multiple--relaxation--time lattice Boltzmann models in three dimensions . Philos. Trans. Roy. Soc. Lond. A: Math. Phys. Eng. Sci. 360 , 1792 (2002), 437--451. Dominique d\u2019Humi\u00e8res. 2002. Multiple--relaxation--time lattice Boltzmann models in three dimensions. Philos. Trans. Roy. Soc. Lond. A: Math. Phys. Eng. Sci. 360, 1792 (2002), 437--451.","journal-title":"Philos. Trans. Roy. Soc. Lond. A: Math. Phys. Eng. Sci."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383260"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130878"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2018.2840334"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.73.066705"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366167"},{"key":"e_1_2_2_22_1","volume-title":"Proceedings of the International Conference on Machine Learning. 399--406","author":"Gregor Karol","year":"2010","unstructured":"Karol Gregor and Yann LeCun . 2010 . Learning fast approximations of sparse coding . In Proceedings of the International Conference on Machine Learning. 399--406 . Karol Gregor and Yann LeCun. 2010. Learning fast approximations of sparse coding. In Proceedings of the International Conference on Machine Learning. 399--406."},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939738"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.105"},{"key":"e_1_2_2_25_1","article-title":"Data-driven fluid simulations using regression forests","volume":"34","author":"Jeong SoHyeon","year":"2015","unstructured":"SoHyeon Jeong , Barbara Solenthaler , Marc Pollefeys , Markus Gross , et\u00a0al. 2015 . Data-driven fluid simulations using regression forests . ACM Trans. Graph. 34 , 6, Article 199 (Oct. 2015), 9 pages. SoHyeon Jeong, Barbara Solenthaler, Marc Pollefeys, Markus Gross, et\u00a0al. 2015. Data-driven fluid simulations using regression forests. ACM Trans. Graph. 34, 6, Article 199 (Oct. 2015), 9 pages.","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766996"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.868164"},{"key":"e_1_2_2_28_1","volume-title":"Proceedings of the Conference on High-performance Graphics. ACM\/Eurographics, 33--37","author":"Karras Tero","year":"2012","unstructured":"Tero Karras . 2012 . Maximizing parallelism in the construction of BVHs, octrees, and k-d trees . In Proceedings of the Conference on High-performance Graphics. ACM\/Eurographics, 33--37 . Tero Karras. 2012. Maximizing parallelism in the construction of BVHs, octrees, and k-d trees. In Proceedings of the Conference on High-performance Graphics. ACM\/Eurographics, 33--37."},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964988"},{"key":"e_1_2_2_30_1","volume-title":"Deep fluids: A generative network for parameterized fluid simulations. Comput. Graph. Forum 38, 2","author":"Kim Byungsoo","year":"2019","unstructured":"Byungsoo Kim , Vinicius C. Azevedo , Nils Thuerey , Theodore Kim , Markus Gross , and Barbara Solenthaler . 2019. Deep fluids: A generative network for parameterized fluid simulations. Comput. Graph. Forum 38, 2 ( 2019 ). Byungsoo Kim, Vinicius C. Azevedo, Nils Thuerey, Theodore Kim, Markus Gross, and Barbara Solenthaler. 2019. Deep fluids: A generative network for parameterized fluid simulations. Comput. Graph. Forum 38, 2 (2019)."},{"key":"e_1_2_2_31_1","volume-title":"Proceedings of the Eurographics Conference on Natural Phenomena. 51--56","author":"Kim ByungMoon","year":"2005","unstructured":"ByungMoon Kim , Yingjie Liu , Ignacio Llamas , and Jarek Rossignac . 2005 . FlowFixer: Using BFECC for fluid simulation . In Proceedings of the Eurographics Conference on Natural Phenomena. 51--56 . ByungMoon Kim, Yingjie Liu, Ignacio Llamas, and Jarek Rossignac. 2005. FlowFixer: Using BFECC for fluid simulation. In Proceedings of the Eurographics Conference on Natural Phenomena. 51--56."},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2008.01144.x"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461987"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360649"},{"key":"e_1_2_2_35_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba . 2014 . Adam : A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141961"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778851"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2859931"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392400"},{"key":"e_1_2_2_40_1","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1109\/TVCG.2012.303","article-title":"Turbulence simulation by adaptive multi-relaxation lattice Boltzmann modeling","volume":"20","author":"Liu Xiaopei","year":"2014","unstructured":"Xiaopei Liu , Wai-Man Pang , Jing Qin , and Chi-Wing Fu . 2014 . Turbulence simulation by adaptive multi-relaxation lattice Boltzmann modeling . IEEE Trans. Vis. Comput. Graph. 20 , 2 (Feb. 2014), 289--302. Xiaopei Liu, Wai-Man Pang, Jing Qin, and Chi-Wing Fu. 2014. Turbulence simulation by adaptive multi-relaxation lattice Boltzmann modeling. IEEE Trans. Vis. Comput. Graph. 20, 2 (Feb. 2014), 289--302.","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015745"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.4866146"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531344"},{"key":"e_1_2_2_44_1","volume-title":"cuBLAS library. 15, 27","author":"Nvidia CUDA","year":"2008","unstructured":"CUDA Nvidia . 2008. cuBLAS library. 15, 27 ( 2008 ), 31. NVIDIA Corporation , Santa Clara, CA . CUDA Nvidia. 2008. cuBLAS library. 15, 27 (2008), 31. NVIDIA Corporation, Santa Clara, CA."},{"key":"e_1_2_2_45_1","volume-title":"A Guide to NumPy","author":"Oliphant Travis E.","unstructured":"Travis E. Oliphant . 2006. A Guide to NumPy . Vol. 1 . Travis E. Oliphant. 2006. A Guide to NumPy. Vol. 1."},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073368.1073406"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778803"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766925"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/1882261.1866196"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185608"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322945"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2019406.2019411"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201398"},{"key":"e_1_2_2_54_1","volume-title":"Proceedings of the Symposium on Computer Animation. 1--7.","author":"Schechter H.","unstructured":"H. Schechter and R. Bridson . 2008. Evolving sub-grid turbulence for smoke animation . In Proceedings of the Symposium on Computer Animation. 1--7. H. Schechter and R. Bridson. 2008. Evolving sub-grid turbulence for smoke animation. In Proceedings of the Symposium on Computer Animation. 1--7."},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-007-9166-4"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661269"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531346"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311548"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766904"},{"key":"e_1_2_2_60_1","volume-title":"Proceedings of the International Conference on Machine Learning","volume":"70","author":"Tompson Jonathan","year":"2017","unstructured":"Jonathan Tompson , Kristofer Schlachter , Pablo Sprechmann , and Ken Perlin . 2017 . Accelerating Eulerian fluid simulation with convolutional networks . In Proceedings of the International Conference on Machine Learning , Vol. 70 . 3424--3433. Jonathan Tompson, Kristofer Schlachter, Pablo Sprechmann, and Ken Perlin. 2017. Accelerating Eulerian fluid simulation with convolutional networks. In Proceedings of the International Conference on Machine Learning, Vol. 70. 3424--3433."},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13522"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201325"},{"key":"e_1_2_2_63_1","article-title":"An efficient construction of reduced deformable objects","volume":"32","author":"Tycowicz Christoph Von","year":"2013","unstructured":"Christoph Von Tycowicz , Christian Schulz , Hans-Peter Seidel , and Klaus Hildebrandt . 2013 . An efficient construction of reduced deformable objects . ACM Trans. Graph. 32 , 6, Article 213 (Nov. 2013), 10 pages. Christoph Von Tycowicz, Christian Schulz, Hans-Peter Seidel, and Klaus Hildebrandt. 2013. An efficient construction of reduced deformable objects. ACM Trans. Graph. 32, 6, Article 213 (Nov. 2013), 10 pages.","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778852"},{"key":"e_1_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778852"},{"key":"e_1_2_2_66_1","volume-title":"A multi-pass GAN for fluid flow super-resolution. arXiv preprint arXiv:1906.01689","author":"Werhahn Maximilian","year":"2019","unstructured":"Maximilian Werhahn , You Xie , Mengyu Chu , and Nils Thuerey . 2019. A multi-pass GAN for fluid flow super-resolution. arXiv preprint arXiv:1906.01689 ( 2019 ). Maximilian Werhahn, You Xie, Mengyu Chu, and Nils Thuerey. 2019. A multi-pass GAN for fluid flow super-resolution. arXiv preprint arXiv:1906.01689 (2019)."},{"key":"e_1_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073713"},{"key":"e_1_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201304"},{"key":"e_1_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2050625"},{"key":"e_1_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201324"},{"key":"e_1_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661261"},{"key":"e_1_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766982"},{"key":"e_1_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925910"},{"key":"e_1_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461999"},{"key":"e_1_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073298"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3412360","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3412360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:25:01Z","timestamp":1750195501000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3412360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,18]]},"references-count":75,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,2,28]]}},"alternative-id":["10.1145\/3412360"],"URL":"https:\/\/doi.org\/10.1145\/3412360","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,18]]},"assertion":[{"value":"2019-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-09-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}