Journal of Visualization

, Volume 20, Issue 2, pp 195–204 | Cite as

Massively parallel inverse rendering using Multi-objective Particle Swarm Optimization

  • Koki Nagano
  • Thomas Collins
  • Chi-An Chen
  • Aiichiro Nakano
Regular Paper
  • 136 Downloads

Abstract

We present a novel GPU-accelerated per-pixel inverse rendering optimization algorithm based on Particle Swarm Optimization (PSO). Our algorithm estimates the per-pixel scene attributes—including reflectance properties—of a 3D model, and is fast enough to do in situ visualization of the optimization in real-time. The algorithm’s high parallel efficiency is demonstrated through our GPU/GLSL shader implementation of the method. IRPSO is validated experimentally on simulated ground truth images, while a suite of tests performed on the University of Southern California’s High Performance Computing Center cluster provides strong evidence that our method can scale to larger, more difficult inverse rendering problems.

Graphical abstract

Keywords

Inverse rendering Particle Swarm Optimization GPU acceleration In situ visualization 

References

  1. Chow CK, Tsui HT (2004) Autonomous agent response learning by a multi-species particle swarm optimization. In: IEEE CEC2004 congress on evolutionary computation, 2004, vol 1, pp 778–785Google Scholar
  2. Cook RL, Torrance KE (1982) A reflectance model for computer graphics. ACM TOG 1(1):7–24CrossRefGoogle Scholar
  3. Debevec PE, Taylor CJ, Malik J (1996) Modeling and rendering architecture from photographs: a hybrid geometry- and image-based approach. In: Proceedings of SIGGRAPH 96, computer graphics proceedings, annual conference series, pp 11–20Google Scholar
  4. Donner C, Weyrich T, d’Eon E, Ramamoorthi R, Rusinkiewicz S (2008) A layered, heterogeneous reflectance model for acquiring and rendering human skin. In: ACM TOG (Proceedings of SIGGRAPH Asia)Google Scholar
  5. Eberhart R, Kennedy J (1995) A new optimizer using particle swarm theory. In: Proceedings of the sixth international symposium on micro machine and human science, 1995, MHS ’95, pp 39–43. doi:10.1109/MHS.1995.494215
  6. Ghosh A, Fyffe G, Tunwattanapong B, Busch J, Yu X, Debevec P (2011) Multiview face capture using polarized spherical gradient illumination. In: Proceedings of the 2011 SIGGRAPH Asia conference, SA ’11. ACM, New York, pp 129:1–129:10. doi:10.1145/2024156.2024163
  7. Graham P, Tunwattanapong B, Busch J, Yu X, Jones A, Debevec P, Ghosh A (2013) Measurement-based synthesis of facial microgeometry. Comput Graphics Forum 32(2pt3):335–344. doi:10.1111/cgf.12053
  8. Marschner S (1998) Inverse rendering for computer graphics. Ph.D. thesis, Cornell UniversityGoogle Scholar
  9. Nagano K, Collins T, Chen CA, Nakano A (2015) GPU-based inverse rendering with multi-objective particle swarm optimization. In: SIGGRAPH Asia 2015 visualization in high performance computing, SA ’15. ACM, New York, pp 8:1–8:4. doi:10.1145/2818517.2818523
  10. Parsopoulos KE, Vrahatis MN (2004) On the computation of all global minimizers through particle swarm optimization. IEEE Trans Evol Comput 8(3):211–224CrossRefGoogle Scholar
  11. Parsopoulos KE, Vrahatis MN (2008) Multi-objective particles swarm optimization approaches. In: Thu Bui L, Alam S (eds) Multi-objective optimization in computational intelligence: theory and practice. IGI Global, Hershey, pp 20–42Google Scholar
  12. Poli R (2008) Analysis of the publications on the applications of particle swarm optimisation. J Artif Evol App 4:1–4:10. doi:10.1155/2008/685175
  13. Ramamoorthi R, Hanrahan P (2001) A signal-processing framework for inverse rendering. In: Proceedings of the 28th annual conference on computer graphics and interactive techniques, SIGGRAPH ’01. ACM, New York, pp 117–128. doi:10.1145/383259.383271
  14. Sun J, Lai C, Wu X (2011) Particle swarm optimisation: classical and quantum perspectives. Chapman & Hall, LondonGoogle Scholar
  15. Weyrich T, Matusik W, Pfister H, Bickel B, Donner C, Tu C, McAndless J, Lee J, Ngan A, Jensen HW, Gross M (2006) Analysis of human faces using a measurement-based skin reflectance model. ACM Trans Graph 25(3):1013–1024CrossRefGoogle Scholar
  16. Yu Y, Debevec P, Malik J, Hawkins T (1999) Inverse global illumination: recovering reflectance models of real scenes from photographs. In: SIGGRAPH ’99, pp 215–224Google Scholar

Copyright information

© The Visualization Society of Japan 2016

Authors and Affiliations

  • Koki Nagano
    • 1
  • Thomas Collins
    • 1
  • Chi-An Chen
    • 1
  • Aiichiro Nakano
    • 1
  1. 1.University of Southern CaliforniaLos AngelesUSA

Personalised recommendations