FlowTexNet: Fast Texture Synthesis for Massive Flow Field Visualization
Authors: 
Zijian Kang, Wenyao Zhang, Na WangAuthors Info & Claims
Zijian Kang, Wenyao Zhang, Na WangAuthors Info & ClaimsAbstract
Flow field texture synthesis is a common and popular way to visualize flow fields. When massive flow fields are to be processed, existing algorithms based on line integral convolution (LIC) are not fast enough. In this paper, a new deep-learning-based method is proposed to synthesize flow textures for massive flow fields. Firstly, a deep neural network called FlowTexNet is built on the base of encoder-decoder architecture. Then the network is trained by flow textures generated by the original LIC algorithm. By this way, FlowTexNet can synthesize flow textures that have the same visualization effect as LIC textures. But FlowTexNet is much faster than the LIC algorithm. Test results show that the speedup of FlowTexNet is up to 450x when it is used to process massive flow fields and compared with the original LIC algorithm. Moreover, FlowTexNet can be applied to flow fields that are out of training, showing good generalization performance.
References
[1]
Laramee, R. S., Hauser, H., Doleisch, H., Vrolijk, B., Post, F. H., and Weiskopf, D. 2004. The state of the art in flow visualization: Dense and texture‐based techniques. Computer Graphics Forum, 23, 2, 203–221. https://doi.org/10.1111/j.1467-8659.2004.00753.x.
[2]
Brian Cabral and Leith Casey Leedom. 1993. Imaging vector fields using line integral convolution. In Proceedings of the 20th annual conference on Computer graphics and interactive techniques (SIGGRAPH '93). Association for Computing Machinery, New York, NY, USA, 263–270. https://doi.org/10.1145/166117.166151.
[3]
Detlev Stalling and Hans-Christian Hege. 1995. Fast and resolution independent line integral convolution. In Proceedings of the 22nd annual conference on Computer graphics and interactive techniques (SIGGRAPH '95). Association for Computing Machinery, New York, NY, USA, 249–256. https://doi.org/10.1145/218380.218448.
[4]
Bo Qin, Zhanbin Wu, Fang Su, and Titi Pang. 2010. GPU-Based parallelization algorithm for 2d line integral convolution. In Proceedings of the First international conference on Advances in Swarm Intelligence - Volume Part I (ICSI'10). Springer-Verlag, Berlin, Heidelberg, 397–404. https://doi.org/10.1007/978-3-642-13495-1_49.
[5]
Redouane Lguensat, Miao Sun, Ronan Fablet, Pierre Tandeo, Evan Mason and Ge Chen. 2018. EddyNet: A deep neural network for pixel-wise classification of oceanic eddies. IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium. IEEE, Valencia, Spain, 1764-1767. https://doi.org/10.1109/IGARSS.2018.8518411.
[6]
Liang Deng, Wenchun Bao, Yueqing Wang, Zhigong Yang, Dan Zhao, Fang Wang, Chongke Bi, and Yang Guo. 2022. Vortex-U-Net: An efficient and effective vortex detection approach based on U-Net structure. Appl. Soft Computing. 115, C (Jan 2022). https://doi.org/10.1016/j.asoc.2021.108229.
[7]
Yang Liu, Yutong Lu, Yueqing Wang, Dong Sun, Liang Deng, FangWang and Yan Lei. 2019. A CNN-based shock detection method in flow visualization. Computers & Fluids. 184(2019), 1-9. https://doi.org/10.1016/j.compfluid.2019.03.022.
[8]
Octavi Obiols-Sales, Abhinav Vishnu, Nicholas Malaya, and Aparna Chandramowliswharan. 2020. CFDNet: a deep learning-based accelerator for fluid simulations. In Proceedings of the 34th ACM International Conference on Supercomputing (ICS '20). Association for Computing Machinery, New York, NY, USA, Article 3, 1–12. https://doi.org/10.1145/3392717.3392772.
[9]
Pin Wu, Kaikai Pan, Lulu Ji, Siquan Gong, Weibing Feng, Wenyan Yuan, and Christopher Pain. 2022. Navier–stokes Generative Adversarial Network: a physics-informed deep learning model for fluid flow generation. Neural Computing. Appl. 34, 14 (Jul 2022), 11539–11552. https://doi.org/10.1007/s00521-022-07042-6.
[10]
Jarke J. van Wijk. 1991. Spot noise texture synthesis for data visualization. In Proceedings of the 18th annual conference on Computer graphics and interactive techniques (SIGGRAPH '91). Association for Computing Machinery, New York, NY, USA, 309–318. https://doi.org/10.1145/122718.122751.
[11]
Nelson Max, Roger Crawfis, and Dean Williams. 1992. Visualizing wind velocities by advecting cloud textures. In Proceedings of the 3rd conference on Visualization '92 (VIS '92). IEEE Computer Society Press, Washington, DC, USA, 179–184. https://doi.org/10.1109/VISUAL.1992.235210.
[12]
Malte Zöckler, Detlev Stalling, and Hans-Christian Hege. 1997. Parallel line integral convolution. Parallel Computing. 23, 7 (July 1997), 975–989. https://doi.org/10.1016/S0167-8191(97)00039-2.
[13]
Rajat Kumar Sinha, Ruchi Pandey, Rohan Pattnaik. 2018. Deep learning for computer vision tasks: a review. 2017 International Conference on Intelligent Computing and Control (I2C2). https://doi.org/10.48550/arXiv.1804.03928.
[14]
Daniel W Otter, Julian R Medina and Jugal K Kalita. 2020. A survey of the usages of deep learning for natural language processing. IEEE Transactions on Neural Networks and Learning Systems, 32, 2 (February 2021) 604 – 624. https://doi.org/10.1109/TNNLS.2020.2979670.
[15]
Zijun Duo, Wenke Wang and Huizan Wang. 2019. Oceanic mesoscale eddy detection method based on deep learning. Remote Sensing, 11, 16(August 2019), 1921. https://doi.org/10.3390/rs11161921.
[16]
Liang Deng, Yueqing Wang, Yang Liu, Fang Wang, Sikun Li, and Jie Liu. 2019. A CNN-based vortex identification method. J. Vis. 22, 1 (February 2019), 65–78. https://doi.org/10.1007/s12650-018-0523-1.
[17]
Yueqing Wang, Liang Deng, Zhigong Yang, Dan Zhao, and Fang Wang. 2021. A rapid vortex identification method using fully convolutional segmentation network. Vis. Comput. 37, 2 (Feburary 2021), 261–273. https://doi.org/10.1007/s00371-020-01797-6.
[18]
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI 2015: Medical Image Computing and Computer-Assisted Intervention. Lecture Notes in Computer Science, 234-241. https://doi.org/10.1007/978-3-319-24574-4_28.
[19]
Dmitry Ulyanov and A. Vedaldi, V. Lempitsky. 2016. Instance normalization: The missing ingredient for fast stylization. https://doi.org/10.48550/arXiv.1607.08022.
[20]
Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Las Vegas, NV, USA. https://doi.org/10.1109/CVPR.2016.90.
[21]
Qing-Long Zhang and Yu-Bin Yang. 2021. SA-Net: Shuffle Attention for Deep Convolutional Neural Networks. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE Toronto, ON, Canada. 2235-2239. https://doi.org 10.1109/ICASSP39728.2021.9414568.
[22]
Perry, Anthony E. and B. D. Fairlie. 1979. Critical Points in Flow Patterns. Advances in Geophysics, 18 (1975), 299-315. https://doi.org/10.1016/S0065-2687(08)60588-9.
Index Terms
- FlowTexNet: Fast Texture Synthesis for Massive Flow Field Visualization
Index terms have been assigned to the content through auto-classification.
Recommendations
Directional enhancement in texture-based vector field visualization
GRAPHITE '06: Proceedings of the 4th international conference on Computer graphics and interactive techniques in Australasia and Southeast AsiaThe use of textures provides a rich and diverse set of possibilities for the visualization of flow data. In this paper, we present methods designed to produce oriented and controlled textures that accurately reflect the complex patterns that occur in ...
Image-Space Texture-Based Output-Coherent Surface Flow Visualization
Image-space line integral convolution (LIC) is a popular scheme for visualizing surface vector fields due to its simplicity and high efficiency. To avoid inconsistencies or color blur during the user interactions, existing approaches employ surface ...
Fast flow visualization on CUDA based on texture optimization
AMT'12: Proceedings of the 8th international conference on Active Media TechnologyFlow visualization plays an important role in many scientific visualization applications. It is effective to visualize flow fields with moving textures which vividly capture the properties of flow field through varying texture appearances.Texture-...
Comments
Information & Contributors
Information
Published In
March 2023
598 pages
ISBN:9781450399449
DOI:10.1145/3590003
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 29 May 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- State Key Laboratory of Computer Architecture (ICT, CAS)
Conference
CACML 2023
CACML 2023: 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning
March 17 - 19, 2023
Shanghai, China
Acceptance Rates
CACML '23 Paper Acceptance Rate 93 of 241 submissions, 39%;
Overall Acceptance Rate 93 of 241 submissions, 39%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 22Total Downloads
- Downloads (Last 12 months)16
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Sep 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format