Abstract
We propose a method of three-dimensional (3D) modeling of volumetric fluid phenomena from sparse multi-view images (e.g., only a single-view input or a pair of front- and side-view inputs). The volume determined from such sparse inputs using previous methods appears blurry and unnatural with novel views; however, our method preserves the appearance of novel viewing angles by transferring the appearance information from input images to novel viewing angles. For appearance information, we use histograms of image intensities and steerable coefficients. We formulate the volume modeling as an energy minimization problem with statistical hard constraints, which is solved using an expectation maximization (EM)-like iterative algorithm. Our algorithm begins with a rough estimate of the initial volume modeled from the input images, followed by an iterative process whereby we first render the images of the current volume with novel viewing angles. Then, we modify the rendered images by transferring the appearance information from the input images, and we thereafter model the improved volume based on the modified images. We iterate these operations until the volume converges. We demonstrate our method successfully provides natural-looking volume sequences of fluids (i.e., fire, smoke, explosions, and a water splash) from sparse multi-view videos. To create production-ready fluid animations, we further propose a method of rendering and editing fluids using a commercially available fluid simulator.
Supplemental Material
Available for Download
Supplemental files
- Atcheson, B., Ihrke, I., Heidrich, W., Tevs, A., Bradley, D., Magnor, M., and Seidel, H.-P. 2008. Time-resolved 3d capture of non-stationary gas flows. ACM Trans. Graph. 27, 5, 132:1--132:9. Google ScholarDigital Library
- Bhat, K. S., Seitz, S. M., Hodgins, J. K., and Khosla, P. K. 2004. Flow-based video synthesis and editing. ACM Trans. Graph. 23, 3, 360--363. Google ScholarDigital Library
- Bridson, R., and Müller-Fischer, M. 2007. Fluid simulation: Siggraph 2007 course notes. In ACM SIGGRAPH 2007 Courses, 1--81. Google ScholarDigital Library
- Debevec, P. 2001. Light probe image gallery. Available at http://www.pauldebevec.com/Probes/.Google Scholar
- Debevec, P. 2006. High-resolution light probe image gallery. Available at http://gl.ict.usc.edu/Data/HighResProbes/.Google Scholar
- Dong, Y., Lefebvre, S., Tong, X., and Drettakis, G. 2008. Lazy solid texture synthesis. In Proc. of EGSR '08, 1165--1174. Google ScholarDigital Library
- Gregson, J., Krimerman, M., Hullin, M. B., and Heidrich, W. 2012. Stochastic tomography and its applications in 3d imaging of mixing fluids. ACM Trans. Graph. 31, 4, 52:1--52:10. Google ScholarDigital Library
- Gregson, J., Heide, F., Hullin, M. B., Rouf, M., and Heidrich, W. 2013. Stochastic deconvolution. In Proc. of CVPR 2013, 1043--1050. Google ScholarDigital Library
- Gregson, J., Ihrke, I., Thuerey, N., and Heidrich, W. 2014. From capture to simulation: Connecting forward and inverse problems in fluids. ACM Trans. Graph. 33, 4, 139:1--139:11. Google ScholarDigital Library
- Gu, J., Nayar, S., Grinspun, E., Belhumeur, P., and Ramamoorthi, R. 2013. Compressive structured light for recovering inhomogeneous participating media. IEEE Trans. Pattern Anal. Mach. Intell. 35, 3, 555--566.Google Scholar
- Hasinoff, S. W., and Kutulakos, K. N. 2007. Photo-consistent reconstruction of semitransparent scenes by densitysheet decomposition. IEEE Trans. Pattern Anal. Mach. Intell. 29, 5, 870--885. Google ScholarDigital Library
- Hawkins, T., Einarsson, P., and Debevec, P. 2005. Acquisition of time-varying participating media. ACM Trans. Graph. 24, 3, 812--815. Google ScholarDigital Library
- Heeger, D. J., and Bergen, J. R. 1995. Pyramid-based texture analysis/synthesis. In Proc. of SIGGRAPH '95, 229--238. Google ScholarDigital Library
- Ihrke, I., and Magnor, M. 2004. Image-based tomographic reconstruction of flames. In Proc. of SCA '04, 365--373. Google ScholarDigital Library
- Jagnow, R., Dorsey, J., and Rushmeier, H. 2004. Stereological techniques for solid textures. ACM Trans. Graph. 23, 3, 329--335. Google ScholarDigital Library
- Kak, A. C., and Slaney, M. 1988. Principles of computerized tomographic imaging. IEEE Press.Google Scholar
- Klehm, O., Ihrke, I., Seidel, H.-P., and Eisemann, E. 2013. Volume stylizer: Tomography-based volume painting. In Proc of I3D '13, 161--168. Google ScholarDigital Library
- Kopf, J., Fu, C.-W., Cohen-Or, D., Deussen, O., Lischinski, D., and Wong, T.-T. 2007. Solid texture synthesis from 2d exemplars. ACM Trans. Graph. 26, 3, 2:1--2:9. Google ScholarDigital Library
- Kwatra, V., Essa, I., Bobick, A., and Kwatra, N. 2005. Texture optimization for example-based synthesis. ACM Trans. Graph. 24, 3, 795--802. Google ScholarDigital Library
- Li, C., Pickup, D., Saunders, T., Cosker, D., Marshall, D., Hall, P., and Willis, P. 2013. Water surface modeling from a single viewpoint video. IEEE Trans. Vis. Comput. Graphics 19, 7, 1242--1251. Google ScholarDigital Library
- Liu, Z., Hu, Y., and Qi, Y. 2011. Modeling of smoke from a single view. In Proc. of ICVRV '11, 291--294. Google ScholarDigital Library
- Ma, C., Wei, L.-Y., Lefebvre, S., and Tong, X. 2013. Dynamic element textures. ACM Trans. Graph. 32, 4, 90:1--90:10. Google ScholarDigital Library
- Portilla, J., and Simoncelli, E. P. 2000. A parametric texture model based on joint statistics of complex wavelet coefficients. Int. J. Comput. Vis. 40, 1, 49--70. Google ScholarDigital Library
- Qin, X., and Yang, Y.-H. 2007. Aura 3d textures. IEEE Trans. Vis. Comput. Graph. 13, 2, 379--389. Google ScholarDigital Library
- Reche-Martinez, A., Martin, I., and Drettakis, G. 2004. Volumetric reconstruction and interactive rendering of trees from photographs. ACM Trans. Graph. 23, 3, 720--727. Google ScholarDigital Library
- Takayama, K., Okabe, M., Ijiri, T., and Igarashi, T. 2008. Lapped solid textures: Filling a model with anisotropic textures. ACM Trans. Graph. 27, 3, 53:1--53:9. Google ScholarDigital Library
- Thürey, N., Keiser, R., Pauly, M., and Rüde, U. 2006. Detail-preserving fluid control. In Proc. of SCA '06, 7--12. Google ScholarDigital Library
- Wei, L.-Y. 2002. Texture Synthesis by Fixed Neighborhood Searching. PhD thesis. Google ScholarDigital Library
- Wenger, S., Lorenz, D., and Magnor, M. 2013. Fast image-based modeling of astronomical nebulae. Comput. Graph. Forum 32, 7, 93--100.Google ScholarCross Ref
- Werlberger, M., Pock, T., and Bischof, H. 2010. Motion estimation with non-local total variation regularization. In Proc. of CVPR 2010, 2464--2471.Google Scholar
- Wexler, Y., Shechtman, E., and Irani, M. 2007. Space-time completion of video. IEEE Trans. Pattern Anal. Mach. Intell. 29, 3, 463--476. Google ScholarDigital Library
Index Terms
- Fluid volume modeling from sparse multi-view images by appearance transfer
Recommendations
A Model for Volume Lighting and Modeling
Direct volume rendering is a commonly used technique in visualization applications. Many of these applications require sophisticated shading models to capture subtle lighting effects and characteristics of volumetric data and materials. For many volumes,...
Interactive translucent volume rendering and procedural modeling
VIS '02: Proceedings of the conference on Visualization '02Direct volume rendering is a commonly used technique in visualization applications. Many of these applications require sophisticated shading models to capture subtle lighting effects and characteristics of volumetric data and materials. Many common ...
Interactive Relighting in Single Low-Dynamic Range Images
This article addresses the relighting of outdoor and large indoor scenes illuminated by nondistant lights, which has seldom been discussed in previous works. We propose a method for users to interactively edit the illumination of a scene by moving ...
Comments