Abstract
We present radiance regression functions for fast rendering of global illumination in scenes with dynamic local light sources. A radiance regression function (RRF) represents a non-linear mapping from local and contextual attributes of surface points, such as position, viewing direction, and lighting condition, to their indirect illumination values. The RRF is obtained from precomputed shading samples through regression analysis, which determines a function that best fits the shading data. For a given scene, the shading samples are precomputed by an offline renderer.
The key idea behind our approach is to exploit the nonlinear coherence of the indirect illumination data to make the RRF both compact and fast to evaluate. We model the RRF as a multilayer acyclic feed-forward neural network, which provides a close functional approximation of the indirect illumination and can be efficiently evaluated at run time. To effectively model scenes with spatially variant material properties, we utilize an augmented set of attributes as input to the neural network RRF to reduce the amount of inference that the network needs to perform. To handle scenes with greater geometric complexity, we partition the input space of the RRF model and represent the subspaces with separate, smaller RRFs that can be evaluated more rapidly. As a result, the RRF model scales well to increasingly complex scene geometry and material variation. Because of its compactness and ease of evaluation, the RRF model enables real-time rendering with full global illumination effects, including changing caustics and multiple-bounce high-frequency glossy interreflections.
Supplemental Material
Available for Download
Supplemental material.
- Beale, M. H., Hagan, M. T., and Demuth, H. B. 2012. Neural Network Toolbox user's guide.Google Scholar
- Blum, E., and Li, L. 1991. Approximation theory and feedforward networks. Neural Networks 4, 4, 511--515. Google ScholarDigital Library
- Chester, D. 1990. Why two hidden layers are better than one. In Int. Joint Conf. on Neural Networks (IJCNN), 265--268.Google Scholar
- Cohen, M. F., Wallace, J., and Hanrahan, P. 1993. Radiosity and realistic image synthesis. Academic Press Professional, Inc., San Diego, CA, USA. Google ScholarDigital Library
- Crassin, C., Neyret, F., Sainz, M., Green, S., and Eisemann, E. 2011. Interactive indirect illumination using voxel cone tracing. Computer Graphics Forum 30, 7.Google ScholarCross Ref
- Dachsbacher, C., and Stamminger, M. 2006. Splatting indirect illumination. In I3D, 93--100. Google ScholarDigital Library
- Dachsbacher, C., Stamminger, M., Drettakis, G., and Durand, F. 2007. Implicit visibility and antiradiance for interactive global illumination. ACM Trans. Graph. 26. Google ScholarDigital Library
- Dachsbacher, C. 2011. Analyzing visibility configurations. IEEE Trans. Vis. Comput. Graph. 17, 4, 475--486. Google ScholarDigital Library
- Dong, Z., Kautz, J., Theobalt, C., and Seidel, H.-P. 2007. Interactive global illumination using implicit visibility. In Pacific Conference on Computer Graphics and Applications, 77--86. Google ScholarDigital Library
- Donikian, M., Walter, B., Bala, K., Fernandez, S., and Greenberg, D. P. 2006. Accurate direct illumination using iterative adaptive sampling. IEEE TVCG 12 (May), 353--364. Google ScholarDigital Library
- Donnelly, W., and Lauritzen, A. 2006. Variance shadow maps. In I3D, 161--165. Google ScholarDigital Library
- FAQ. How many hidden layers should I use? Neural Network FAQ, Usenet newsgroup comp.ai.neural-nets, ftp://ftp.sas.com/pub/neural/FAQ3.html#A_hl.Google Scholar
- Green, P., Kautz, J., Matusik, W., and Durand, F. 2006. View-dependent precomputed light transport using nonlinear gaussian function approximations. In I3D, 7--14. Google ScholarDigital Library
- Grzeszczuk, R., Terzopoulos, D., and Hinton, G. 1998. Neuroanimator: fast neural network emulation and control of physics-based models. In Proc. SIGGRAPH '98, 9--20. Google ScholarDigital Library
- Hagan, M., and Menhaj, M. 1994. Training feedforward networks with the marquardt algorithm. Neural Networks, IEEE Transactions on 5, 6, 989--993. Google ScholarDigital Library
- Hastie, T., Tibshirani, R., and Friedman, J. 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2 ed. Springer.Google Scholar
- Hašan, M., Pellacini, F., and Bala, K. 2006. Direct-to-indirect transfer for cinematic relighting. ACM Trans. Graph. 25, 1089--1097. Google ScholarDigital Library
- Hertzmann, A. 2003. Machine learning for computer graphics: A manifesto and tutorial. In Pacific Conference on Computer Graphics and Applications, 22--36. Google ScholarDigital Library
- Hinton, G. E. 1989. Connectionist learning procedures. Artificial Intelligence 40, 1--3, 185--234. Google ScholarDigital Library
- Hornik, K., Stinchcombe, M., and White, H. 1989. Multi-layer feedforward networks are universal approximators. Neural Networks 2, 5 (July), 359--366. Google ScholarDigital Library
- Jakob, W., 2010. Mitsuba renderer. Department of Computer Science, Cornell University. (http://www.mitsuba-renderer.org).Google Scholar
- Kaplanyan, A., and Dachsbacher, C. 2010. Cascaded light propagation volumes for real-time indirect illumination. In I3D, 99--107. Google ScholarDigital Library
- Keller, A. 1997. Instant radiosity. In SIGGRAPH '97, 49--56. Google ScholarDigital Library
- Kontkanen, J., Turquin, E., Holzschuch, N., and Sillion, F. X. 2006. Wavelet radiance transport for interactive indirect lighting. In Rendering Techniques '06, 161--171. Google ScholarDigital Library
- Kristensen, A. W., Akenine-Möller, T., and Jensen, H. W. 2005. Precomputed local radiance transfer for real-time lighting design. ACM Trans. Graph. 24, 1208--1215. Google ScholarDigital Library
- Lafortune, E. P., and Willems, Y. D. 1993. Bi-directional path tracing. In Proc. Compugraphics '93, 145--153.Google Scholar
- Lehtinen, J., Zwicker, M., Turquin, E., Kontkanen, J., Durand, F., Sillion, F. X., and Aila, T. 2008. A meshless hierarchical representation for light transport. ACM Trans. Graph. 27, 37:1--37:9. Google ScholarDigital Library
- Liu, X., Sloan, P.-P., Shum, H.-Y., and Snyder, J. 2004. All-frequency precomputed radiance transfer for glossy objects. In Rendering Techniques '04, 337--344. Google ScholarDigital Library
- McGuire, M., and Luebke, D. 2009. Hardware-accelerated global illumination by image space photon mapping. In High Performance Graphics. Google ScholarDigital Library
- McKay, M. D., Beckman, R. J., and Conover, W. J. 2000. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 42, 1 (Feb.), 55--61. Google ScholarDigital Library
- Meyer, M., and Anderson, J. 2007. Key point subspace acceleration and soft caching. ACM Trans. Graph. 26, 3. Google ScholarDigital Library
- Ng, R., Ramamoorthi, R., and Hanrahan, P. 2004. Triple product wavelet integrals for all-frequency relighting. ACM Trans. Graph. 23, 477--487. Google ScholarDigital Library
- Nichols, G., and Wyman, C. 2010. Interactive indirect illumination using adaptive multiresolution splatting. IEEE TVCG 16, 5, 729--741. Google ScholarDigital Library
- Nowrouzezahrai, D., Kalogerakis, E., and Fiume, E. 2009. Shadowing dynamic scenes with arbitrary brdfs. Comput. Graph. Forum: Eurographics Conf. 28, 249--258.Google ScholarCross Ref
- Parker, S. G., Bigler, J., Dietrich, A., Friedrich, H., Hoberock, J., Luebke, D., McAllister, D., McGuire, M., Morley, K., Robison, A., and Stich, M. 2010. Optix: A general purpose ray tracing engine. ACM Trans. Graph. 29. Google ScholarDigital Library
- Ramamoorthi, R. 2009. Precomputation-based rendering. Found. Trends. Comput. Graph. Vis. 3 (April), 281--369. Google ScholarDigital Library
- Ritschel, T., Grosch, T., Kim, M. H., Seidel, H.-P., Dachsbacher, C., and Kautz, J. 2008. Imperfect shadow maps for efficient computation of indirect illumination. ACM Trans. Graph. 27, 129:1--129:8. Google ScholarDigital Library
- Ritschel, T., Dachsbacher, C., Grosch, T., and Kautz, J. 2012. The state of the art in interactive global illumination. Computer Graphics Forum 31, 1, 160--188. Google ScholarDigital Library
- Sloan, P.-P., Kautz, J., and Snyder, J. 2002. Precomputed radiance transfer for real-time rendering in dynamic, low-frequency lighting environments. ACM Trans. Graph. 21. Google ScholarDigital Library
- Sloan, P.-P., Hall, J., Hart, J., and Snyder, J. 2003. Clustered principal components for precomputed radiance transfer. ACM Trans. Graph. 22, 3 (July), 382--391. Google ScholarDigital Library
- Thiedemann, S., Henrich, N., Grosch, T., and Müller, S. 2011. Voxel-based global illumination. In I3D, 103--110. Google ScholarDigital Library
- Tsai, Y.-T., and Shih, Z.-C. 2006. All-frequency precomputed radiance transfer using spherical radial basis functions and clustered tensor approximation. ACM Trans. Graph. 25, 3, 967--976. Google ScholarDigital Library
- Wald, I., Mark, W. R., Guenther, J., Boulos, S., Ize, T., Hunt, W., Parker, S. G., and Shirley, P. 2009. State of the art in ray tracing animated scenes. Computer Graphics Forum 28, 6, 1691--1722.Google ScholarCross Ref
- Wang, R., Tran, J., and Luebke, D. 2006. All-frequency relighting of glossy objects. ACM Trans. Graph. 25, 2, 293--318. Google ScholarDigital Library
- Wang, R., Zhu, J., and Humphreys, G. 2007. Precomputed radiance transfer for real-time indirect lighting using a spectral mesh basis. In Rendering Techniques '07, 13--21. Google ScholarDigital Library
- Wang, R., Wang, R., Zhou, K., Pan, M., and Bao, H. 2009. An efficient gpu-based approach for interactive global illumination. ACM Trans. Graph. 28 (July), 91:1--91:8. Google ScholarDigital Library
- Ward, G. J. 1992. Measuring and modeling anisotropic reflection. In Proc. SIGGRAPH '92, 265--272. Google ScholarDigital Library
Index Terms
- Global illumination with radiance regression functions
Recommendations
Real-time diffuse global illumination using radiance hints
HPG '11: Proceedings of the ACM SIGGRAPH Symposium on High Performance GraphicsGPU-based interactive global illumination techniques are receiving an increasing interest from both the research and the industrial community as real-time graphics applications strive for visually rich and realistic dynamic three-dimensional ...
A BSSRDF model for efficient rendering of fur with global illumination
Physically-based hair and fur rendering is crucial for visual realism. One of the key effects is global illumination, involving light bouncing between different fibers. This is very time-consuming to simulate with methods like path tracing. Efficient ...
Precomputed illuminance composition for real-time global illumination
I3D '16: Proceedings of the 20th ACM SIGGRAPH Symposium on Interactive 3D Graphics and GamesIn this paper we present a new real-time approach for indirect global illumination under dynamic lighting conditions. We use surfels to gather a sampling of the local illumination and propagate the light through the scene using a hierarchy and a set of ...
Comments