“Anisotropic noise” by Goldberg, Zwicker and Durand

Programmable graphics hardware makes it possible to generate procedural noise textures on the fly for interactive rendering. However, filtering and antialiasing procedural noise involves a tradeoff between aliasing artifacts and loss of detail. In this paper we present a technique, targeted at interactive applications, that provides high-quality anisotropic filtering for noise textures. We generate noise tiles directly in the frequency domain by partitioning the frequency domain into oriented subbands. We then compute weighted sums of the subband textures to accurately approximate noise with a desired spectrum. This allows us to achieve high-quality anisotropic filtering. Our approach is based solely on 2D textures, avoiding the memory overhead of techniques based on 3D noise tiles. We devise a technique to compensate for texture distortions to generate uniform noise on arbitrary meshes. We develop a GPU-based implementation of our technique that achieves similar rendering performance as state-of-the-art algorithms for procedural noise. In addition, it provides anisotropic filtering and achieves superior image quality.

1. Ashikhmin, M., and Shirley, P. 2002. Steerable illumination textures. ACM Trans. Graph. 21, 1, 1–19. Google ScholarDigital Library
2. Cook, R. L., and DeRose, T. 2005. Wavelet noise. ACM Trans. Graph. 24, 3, 803–811. Google ScholarDigital Library
3. Efros, A. A., and Freeman, W. T. 2001. Image quilting for texture synthesis and transfer. In Proceedings of SIGGRAPH ’01, 341–346. Google ScholarDigital Library
4. Fournier, A., and Fiume, E. 1988. Constant-time filtering with space-variant kernels. SIGGRAPH Comput. Graph. 22, 4, 229–238. Google ScholarDigital Library
5. Gotsman, C. 1994. Constant-time filtering by singular value decomposition. Comp. Graph. Forum 13, 2, 153–163.Google ScholarCross Ref
6. Green, S. 2005. GPU Gems 2. Addison-Wesley Professional, ch. Implementing Improved Perlin Noise.Google Scholar
7. Gu, X., Gortler, S. J., and Hoppe, H. 2002. Geometry images. ACM Trans. Graph. 21, 3, 355–361. Google ScholarDigital Library
8. Hart, J. C., Carr, N., Kameya, M., Tibbitts, S. A., and Coleman, T. J. 1999. Antialiased parameterized solid texturing simplified for consumer-level hardware implementation. In Proceedings of the ACM SIGGRAPH/EUROGRAPHICS workshop on Graphics hardware, 45–53. Google ScholarDigital Library
9. Hart, J. C. 2001. Perlin noise pixel shaders. In Proceedings of the ACM SIGGRAPH/EUROGRAPHICS workshop on Graphics hardware, 87–94. Google ScholarDigital Library
10. Heckbert, P. 1989. Fundamentals of texture mapping and image warping. Master’s thesis, University of California, Berkeley.Google Scholar
11. Lewis, J. P. 1989. Algorithms for solid noise synthesis. In Proceedings of SIGGRAPH ’89, 263–270. Google ScholarDigital Library
12. Miné, A., and Neyret, F. 1999. Perlin textures in real time using OpenGL. Tech. rep., RR-3713, INRIA.Google Scholar
13. Olano, M. 2005. Modified noise for evaluation on graphics hardware. In Eurographics Symp. on Graphics Hardware, 105–110. Google ScholarDigital Library
14. Peachey, D. 2003. Texturing and Modeling: A Procedural Approach, 3 ed. Morgan Kaufman Publishers Inc., ch. Building procedural textures.Google Scholar
15. Pérez, P., Gangnet, M., and Blake, A. 2003. Poisson image editing. ACM Trans. Graph. 22, 3, 313–318. Google ScholarDigital Library
16. Perlin, K. 1985. An image synthesizer. In Proceedings of SIGGRAPH ’85, 287–296. Google ScholarDigital Library
17. Portilla, J., and Simoncelli, E. P. 2000. A parametric texture model based on joint statistics of complex wavelet coefficients. Int’l Journal of Computer Vision 40, 1 (October), 49–71. Google ScholarDigital Library
18. Simoncelli, E. P., and Freeman, W. T. 1995. The steerable pyramid: A flexible architecture for multi-scale derivative computation. In Second Int’l Conf. on Image Proc., 444–447. Google ScholarDigital Library