Abstract
Many applications in Computer Graphics contain computationally expensive calculations. These calculations are often performed at many points to produce a full solution, even though the subspace of reasonable solutions may be of a relatively low dimension. The calculation of facial articulation and rendering of scenes with global illumination are two example applications that require these sort of computations. In this paper, we present Key Point Subspace Acceleration and Soft Caching, a technique for accelerating these types of computations.
Key Point Subspace Acceleration (KPSA) is a statistical acceleration scheme that uses examples to compute a statistical subspace and a set of characteristic key points. The full calculation is then computed only at these key points and these points are used to provide a subspace based estimate of the entire calculation. The soft caching process is an extension to the KPSA technique where the key points are also used to provide a confidence estimate for the KPSA result. In cases with high anticipated error the calculation will then "fail through" to a full evaluation of all points (a cache miss), while frames with low error can use the accelerated statistical evaluation (a cache hit).
- Guenter, B., Grimm, C., Wood, D., Malvar, H., and Pighin, F. 98. Making faces. In SIGGRAPH '98: Proceedings of the 25th annual conference on Computer graphics and interactive techniques, 55--66. Google ScholarDigital Library
- Harmon, H. H. 1976. Modern factor analysis, 3rd ed. University of Chicago Press.Google Scholar
- Hasan, M., Pellacini, F., and Bala, K. 2006. Direct-to-indirect transfer for cinematic relighting. In SIGGRAPH '06: ACM SIGGRAPH 2006 Papers, ACM Press, New York, NY, USA, 1089--1097. Google ScholarDigital Library
- Hwang, B.-W., Blanz, V., Vetter, T., and Lee, S.-W. 2000. Face reconstruction using a small set of feature points. In Biologically Motivated Computer Vision, 308--315. Google ScholarDigital Library
- James, D. L., and Fatahalian, K. 2003. Precomputing interactive dynamic deformable scenes. ACM Trans. Graph. 22, 3, 879--887. Google ScholarDigital Library
- James, D. L., and Pai, D. K. 2002. Dyrt: dynamic response textures for real time deformation simulation with graphics hardware. In SIGGRAPH '02: Proceedings of the 29th annual conference on Computer graphics and interactive techniques, ACM Press, New York, NY, USA, 582--585. Google ScholarDigital Library
- Jensen, H. W. 1996. Global illumination using photon maps. In Rendering Techniques '96 (Proceedings of the 7th Eurographics Workshop on Rendering). Google ScholarDigital Library
- Kristensen, A. W., Akenine-Moeller, T., and Jensen, H. W. 2005. Precomputed local radiance transfer for real-time lighting design. ACM Transactions on Graphics (SIGGRAPH 2005) 24, 3, 1208--1215. Google ScholarDigital Library
- Kry, P. G., James, D. L., and Pai, D. K. 2002. Eigenskin: real time large deformation character skinning in hardware. In SCA '02: Proceedings of the 2002 ACM SIGGRAPH/Eurographics symposium on Computer animation, 153--159. Google ScholarDigital Library
- Lewis, J. P., Cordner, M., and Fong, N. 2000. Pose space deformation: a unified approach to shape interpolation and skeleton-driven deformation. In SIGGRAPH '00: Proceedings of the 27th annual conference on Computer graphics and interactive techniques, ACM Press/Addison-Wesley Publishing Co., New York, NY, USA, 165--172. Google ScholarDigital Library
- Meyer, M., and Anderson, J. 2006. Statistical acceleration for animated global illumination. ACM Transactions on Graphics (SIGGRAPH 2006) 25, 3, 1075--1080. Google ScholarDigital Library
- Meyer, M., and Anderson, J. 2007. Key point subspace acceleration and soft caching. Tech. Rep. 06--04b, Pixar Animation Studios. http://graphics.pixar.com/SoftCachingB/.Google Scholar
- Mo, Z., Lewis, J., and Neumann, U. 2004. Face inpainting with local linear representations. In BMVC.Google Scholar
- Shashua, A., and Wolf, L. 2004. Kernel feature selection with side data using a spectral approach. In Proceedings of the European Conference on Computer Vision (ECCV).Google Scholar
- Sloan, P.-P., Hall, J., Hart, J., and Snyder, J. 2003. Clustered principal components for precomputed radiance transfer. ACM Trans. Graph. 22, 3, 382--391. Google ScholarDigital Library
- Wang, X. C., and Phillips, C. 2002. Multi-weight enveloping: least-squares approximation techniques for skin animation. In SCA '02: Proceedings of the 2002 ACM SIGGRAPH/Eurographics symposium on Computer animation, ACM Press, New York, NY, USA, 129--138. Google ScholarDigital Library
- Ward, G., and Heckbert, P. 1992. Irradiance Gradients. In Proceedings of the 3rd Eurographics Workshop on Rendering, 85--98.Google Scholar
- Ward, G., Rubinstein, F., and Clear, R. 1988. A Ray Tracing Solution for Diffuse Interreflection. In Computer Graphics (ACM SIGGRAPH '88 Proceedings), 85--92. Google ScholarDigital Library
- Zhang, Q., Liu, Z., Guo, B., and Shum, H. 2003. Geometry-driven photorealistic facial expression synthesis. In SCA '03: Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation, Eurographics Association, Airela-Ville, Switzerland, Switzerland, 177--186. Google ScholarDigital Library
Index Terms
- Key Point Subspace Acceleration and soft caching
Recommendations
Key Point Subspace Acceleration and soft caching
SIGGRAPH '07: ACM SIGGRAPH 2007 papersMany applications in Computer Graphics contain computationally expensive calculations. These calculations are often performed at many points to produce a full solution, even though the subspace of reasonable solutions may be of a relatively low ...
Visual object recognition using probabilistic kernel subspace similarity
Probabilistic subspace similarity-based face matching is an efficient face recognition algorithm proposed by Moghaddam et al. It makes one basic assumption: the intra-class face image set spans a linear space. However, there are yet no rational ...
On some variants of locality preserving projection
High dimensional data is hard to interpret and work with in its raw form; hence dimensionality reduction is applied beforehand to discover underlying low dimensional manifold. Locality Preserving Projection (LPP) was introduced using the concept that ...
Comments