DOI QR코드

DOI QR Code

Quad Tree Based 2D Smoke Super-resolution with CNN

CNN을 이용한 Quad Tree 기반 2D Smoke Super-resolution

  • Received : 2019.06.11
  • Accepted : 2019.06.23
  • Published : 2019.07.14

Abstract

Physically-based fluid simulation takes a lot of time for high resolution. To solve this problem, there are studies that make up the limitation of low resolution fluid simulation by using deep running. Among them, Super-resolution, which converts low-resolution simulation data to high resolution is under way. However, traditional techniques require to the entire space where there are no density data, so there are problems that are inefficient in terms of the full simulation speed and that cannot be computed with the lack of GPU memory as input resolution increases. In this paper, we propose a new method that divides and classifies 2D smoke simulation data into the space using the quad tree, one of the spatial partitioning methods, and performs Super-resolution only required space. This technique accelerates the simulation speed by computing only necessary space. It also processes the divided input data, which can solve GPU memory problems.

물리 기반 유체 시뮬레이션은 고해상도 연산을 위해 많은 시간이 필요하다. 이 문제를 해결하기 위해 저해상도 유체 시뮬레이션의 한계를 딥 러닝으로 보완하는 연구들이 있으며, 그중에서는 저해상도의 시뮬레이션 데이터를 고해상도로 변환해주는 Super-resolution 분야가 있다. 하지만 기존 기법들은 전체 데이터 공간에서 밀도 데이터가 없는 부분까지 연산하므로 전체 시뮬레이션 속도 면에서 효율성이 떨어지며, 입력 해상도가 큰 경우에는 GPU 메모리가 부족해 연산할 수 없는 경우가 발생할 수 있다. 본 연구에서는 공간 분할 법 중 하나인 쿼드 트리를 활용하여 시뮬레이션 공간을 분할 및 분류하여 Super-resolution 하는 기법을 제안한다. 본 기법은 필요 공간만 Super-resolution 하므로 전체 시뮬레이션 가속화가 가능하고, 입력 데이터를 분할 연산하므로 GPU 메모리 문제를 해결할 수 있게 된다.

Keywords

References

  1. J. Tompson, K. Schlachter, P. Sprechmann, K. Perlin, "Accelerating eulerian fluid simulation with convolutional networks", International Conference on Machine Learning (ICML), pages 3424-3433, 2017.
  2. Xiangyun Xiao, Yanqing Zhou, Hui Wang, Xubo Yang "A Novel CNN-based Poisson Solver for Fluid Simulation" IEEE Transactions on Visualization and Computer Graphics (TVCG), page 1-1, 2018
  3. Mengyu Chu and Nils Thuerey, "data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors", ACM Transactions on Graphics (TOG), Volume 36, issue 4, Article No. 69, 2017
  4. You Xie, Erik Franz, Mengyu Chu, Nils Thuerey, "tempoGAN: a temporally coherent, volumetric GAN for super-resolution fluid flow", ACM Transactions on Graphics (TOG), Volume 37, issue 4, Article No. 95, 2018
  5. Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang, "Image Super-Resolution Using Deep Convolutional Networks", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Volume 38, Issue 2, page 295-307, 2016 https://doi.org/10.1109/TPAMI.2015.2439281
  6. Christian Ledig, Lucas Theis , Ferenc Huszar , Jose Caballero , Andrew Cunningham , Alejandro Acosta , Andrew Aitken , Alykhan Tejani , Johannes Totz , Zehan Wang , Wenzhe Shi, "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
  7. Mengyu Chu, You Xie, Laura Leal-Taixe, Nils Thuerey, "Temporally Coherent GANs for Video Super-Resolution (TecoGAN)", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  8. Yifan Wang, Federico Perazzi, Brian McWilliams, Alexander Sorkine-Hornung, Olga Sorkine-Hornung, Christopher Schroers, "A Fully Progressive Approach to Single-Image Super-Resolution", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 864-873, 2018
  9. Gregory M. Hunter, Kenneth Steiglitz, "Operations on Images Using Quad Trees", IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), vol. PAMI-1, No. 2, 1979.
  10. D. Meagher, "Octree encoding: A new technique for the representation, manipulation and display of arbitrary 3d objects by computer", Technical Report IPL-TR-80-111, 1980.
  11. Kun Zhou, Minmin Gong, Xin Huang, Baining Guo, "Data-Parallel Octrees for Surface Reconstruction", IEEE Transactions on Visualization and Computer Graphics (TVCG), Volume 17, Issue 5, page 669-681, 2011 https://doi.org/10.1109/TVCG.2010.75
  12. Gernot Riegler, Ali Osman Ulusoy, Andreas Geiger, "OctNet: Learning Deep 3D Representations at High Resolutions", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), arXiv:1611.05009v4, 2017
  13. Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong, "O-CNN: octree-based convolutional neural networks for 3D shape analysis", ACM Transactions on Graphics (TOG), Volume 36, Issue 4, Article No. 72, 2017
  14. Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox, "Octree Generating Networks: Efficient Convolutional Architectures for High-Resolution 3D Outputs", IEEE International Conference on Computer Vision (ICCV), pp. 2088-2096, 2017
  15. J. Stam "Stable Fluids," ACM SIGGRAPH, Annual Conference Series. 121-128, 1999
  16. Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, "Deep Residual Learning for Image Recognition", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770-778, 2016
  17. Syuhei Sato, Yoshinori Dobashi, Theodore Kim, Tomoyuki NishiTa, "Example-based Turbulence Style Transfer" ACM Transactions on Graphics (TOG), volume 37, issue 4, Article No. 84, 2018

Cited by

  1. Multiple Binarization Quadtree Framework for Optimizing Deep Learning-Based Smoke Synthesis Method vol.26, pp.4, 2021, https://doi.org/10.9708/jksci.2021.26.04.047