
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
Joshua Steinhurst, Greg Coombe, Anselmo Lastra, "Reducing PhotonMapping Bandwidth by Query Reordering," IEEE Transactions on Visualization and Computer Graphics, vol. 14, no. 1, pp. 1324, January/February, 2008.  
BibTex  x  
@article{ 10.1109/TVCG.2007.70413, author = {Joshua Steinhurst and Greg Coombe and Anselmo Lastra}, title = {Reducing PhotonMapping Bandwidth by Query Reordering}, journal ={IEEE Transactions on Visualization and Computer Graphics}, volume = {14}, number = {1}, issn = {10772626}, year = {2008}, pages = {1324}, doi = {http://doi.ieeecomputersociety.org/10.1109/TVCG.2007.70413}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Visualization and Computer Graphics TI  Reducing PhotonMapping Bandwidth by Query Reordering IS  1 SN  10772626 SP13 EP24 EPD  1324 A1  Joshua Steinhurst, A1  Greg Coombe, A1  Anselmo Lastra, PY  2008 KW  Global Illumination KW  Photon Mapping KW  Importance Sampling KW  Irradiance Caching KW  Graphics Hardware VL  14 JA  IEEE Transactions on Visualization and Computer Graphics ER   
Abstract—Photon mapping places an enormous burden on the memory hierarchy. Rendering a 512?512 image of a simple scene can require more than 196GB of raw bandwidth to the photon map data structure. This bandwidth is a major obstacle to real time photon mapping. This paper investigates two approaches for reducing the required bandwidth: 1) reordering the kNN searches; and 2) cache conscious data structures. Using a Hilbert curve reordering, we demonstrate an experimental lower bound of 15MB of bandwidth for the same scene. Unfortunately, this improvement of four orders of magnitude requires a prohibitive amount of intermediate storage. We introduce two novel costeffective algorithms that reduce the bandwidth by one order of magnitude. Scenes of different complexities are shown to exhibit similar reductions in bandwidth. We explain why the choice of data structure does not achieve similar reductions. We also examine the interaction of query reordering with two photon map acceleration techniques, importance sampling and the irradiance cache. Query reordering exploits the additional coherence that arises from the use of importance sampling in scenes with glossy surfaces. Irradiance caching also benefits from query reordering, even when complex surface geometry reduces the effectiveness of the irradiance cache.
[1] H.W. Jensen, Realistic Image Synthesis Using Photon Mapping. AK Peters, 2001.
[2] J. Schmittler, I. Wald, and P. Slusallek, “SaarCOR: A Hardware Architecture for Ray Tracing,” Proc. Graphics Hardware, pp. 2736, 2002.
[3] M. Pharr and P. Hanrahan, “Geometry Caching for RayTracing Displacement Maps,” Proc. Eurographics Workshop Rendering Techniques, pp. 3140, 1996.
[4] F. Dachille IX and A. Kaufman, “GICube: An Architecture for Volumetric Global Illumination and Rendering,” Proc. Graphics Hardware, pp. 119128, 2000.
[5] M. Pharr, C. Kolb, R. Gershbein, and P. Hanrahan, “Rendering Complex Scenes with MemoryCoherent Ray Tracing,” Proc. ACM SIGGRAPH '97, pp. 101108, 1997.
[6] E. Reinhard and E.W. Jansen, “Rendering Large Scenes Using Parallel Ray Tracing,” Proc. First Eurographics Workshop Parallel Graphics and Visualization, pp. 6780, 1996.
[7] C. Faloutsos and S. Roseman, “Fractals for Secondary Key Retrieval,” Proc. Eighth ACM SIGACTSIGMODSIGART Symp. Principles of Database Systems, pp. 247252, 1989.
[8] B. Moon, H.V. Jagadish, C. Faloutsos, and J.H. Saltz, “Analysis of the Clustering Properties of the Hilbert SpaceFilling Curve,” Knowledge and Data Eng., vol. 13, no. 1, pp. 124141, 1996.
[9] J.L. Bentley, “Multidimensional Binary Search Trees Used for Associative Searching,” Comm. ACM, vol. 18, no. 9, pp. 509517, 1975.
[10] V.C.H. Ma and M.D. McCool, “Low Latency Photon Mapping Using Block Hashing,” Proc. Graphics Hardware, pp. 8999, 2002.
[11] J.T. Robinson, “The KDBTree: A Search Structure for Large Multidimensional Dynamic Indexes,” Proc. ACM Sigmod Int'l Conf. the Management of Data, pp. 1018, 1981.
[12] J. Steinhurst, G. Coombe, and A. Lastra, “Reordering for Cache Conscious Photon Mapping,” Proc. Conf. Graphics Interface (GI '05), pp. 97104, 2005.
[13] G. Ward, F. Rubinstein, and R. Clear, “A Ray Tracing Solution for Diffuse Interreflection,” Proc. ACM SIGGRAPH '88, pp. 8692, 1988.
[14] H.W. Jensen, “Global Illumination Using Photon Maps,” Proc. EUROGRAPHICS '96, pp. 2130, 1996.
[15] L. SzirmayKalos, “MonteCarlo Global Illumination Methods— State of the Art and New Developments,” Proc. 15th Spring Conf. Computer Graphics, pp. 321, 1999.
[16] L. Neumann, A. Neumann, and L. SzirmayKalos, “Compact Metallic Reflectance Models,” Proc. EUROGRAPHICS '99, vol. 18, no. 3, pp. 161172, 1999.
[17] E.P. Lafortune and Y.D. Willems, “Using the Modified Phong BRDF for Physically Based Rendering,” Technical Report CW197, Katholieke Univ. Leuven, 1994.
[18] J. Lawrence, S. Rusinkiewicz, and R. Ramamoorthi, “Efficient BRDF Importance Sampling Using a Factored Representation,” Proc. ACM SIGGRAPH '04, vol. 23, pp. 496505, 2004.
[19] G.J. Ward and P.S. Heckbert, “Irradiance Gradients,” Proc. Eurographics Workshop Rendering, pp. 8598, 1992.
[20] P.H. Christensen, “Faster Photon Map Global Illumination,” J.Graphics Tools, vol. 4, no. 3, pp. 110, 1999.
[21] P.H. Christensen and D. Batali, “An Irradiance Atlas for Global Illumination in Complex Production Scenes,” Proc. Eurographics Symp. Rendering, pp. 133141, 2004.
[22] Intel, “Microburst Architecture,” IA32 Intel Architecture Software Developers Manual, vol. 1, pp. 3740, 2003.
[23] W. Jarosz, http:/renderedrealities.net/, Apr. 2004.
[24] M. Pharr and G. Humphreys, Physically Based Rendering from Theory to Implementation. Morgan Kaufmann, 2004.
[25] M.D. Hill and A.J. Smith, “Evaluating Associativity in CPU Caches,” IEEE Trans. Computers, vol. 38, no. 12, pp. 16121630, Dec. 1989.
[26] V. Havran, R. Herzog, and H.P. Seidel, “Fast Final Gathering via Reverse Photon Mapping,” Proc. EUROGRAPHICS '05, pp. 323333, Aug. 2005.
[27] I. Wald, P. Slusallek, C. Benthin, and M. Wagner, “Interactive Rendering with Coherent Ray Tracing,” Proc. EUROGRAPHICS '01, pp. 153164, 2001.
[28] J. McCormack, R. McNamara, C. Gianos, L. Seiler, N.P. Jouppi, and K. Correll, “Neon: A SingleChip 3D Workstation Graphics Accelerator,” Proc. Graphics Hardware, pp. 123132, 1998.
[29] P. Indyk, R. Motwani, P. Raghavan, and S. Vempala, “LocalityPreserving Hashing in Multidimensional Spaces,” Proc. ACM Symp. Theory of Computing (STOC '97), pp. 618625, 1997.
[30] A. Gionis, P. Indyk, and R. Motwani, “Similarity Search in High Dimensions via Hashing,” Proc. Int'l Conf. Very Large Data Bases (VLDB '99), pp. 518529, 1999.
[31] Y. Liu and J. Snoeyink, A Notation for Hilbert Curves to Support Multidimensional Spatial Indexing, work in progress.
[32] S. Singh, “The Photon Pipeline,” Proc. Conf. Computer Graphics and Interactive (GRAPHITE '06), pp. 333340, 2006.
[33] I. Wald, J. Guenther, and P. Slusallek, “Balancing Considered Harmful—Faster Photon Mapping Using the Voxel Volume Heuristic,” Proc. EUROGRAPHICS '04, pp. 595603, 2004.
[34] T.J. Purcell, C. Donner, M. Cammarano, H.W. Jensen, and P. Hanrahan, “Photon Mapping on Programmable Graphics Hardware,” Proc. Graphics Hardware, pp. 4150, July 2003.
[35] R. Bayer and E. McCreight, “Organization and Maintenance of Large Ordered Indexes,” Acta Informatica, vol. 1, no. 3, pp. 173189, 1972.
[36] V. Havran, “Analysis of Cache Sensitive Representations for Binary Space Partitioning Trees,” Informatica, vol. 23, no. 3, pp.203210, May 2000.
[37] NVIDIA, UltraHighEnd Products, http://nvidia.com/pageqfx_uhe.html, Oct. 2004.