DOI: https://doi.org/10.26089/NumMet.v26r207

Adaptation of Global Illumination Computation Methods Based on the Radiosity Algorithm to the Frame Graph Architecture

Authors

  • Alexandr S. Shcherbakov

Keywords:

global illumination
computational graphs
computer graphics

Abstract

This paper examines the integration of the radiosity method into the frame graph architecture to optimize GPU memory consumption. Methods for adapting the multi-bounce matrix method, the local matrix method, and the temporal radiosity method are proposed, considering resource management requirements on the GPU. A scheme for reusing temporal memory across different stages of global illumination processing is described, which helps reduce video memory load and minimize overhead during algorithm execution. An experimental study on test scenes confirms the effectiveness of the proposed approach and demonstrates a reduction in memory consumption.

Downloads

Published

2025-04-02

Issue

Vol. 26 (2025): Issue 2.

Section

Methods and algorithms of computational mathematics and their applications

Author Biography

Alexandr S. Shcherbakov

Lomonosov Moscow State University,
Faculty of Computational Mathematics and Cybernetics
• Junior Researcher

References

  1. F. X. Sillion and C. Puech, Radiosity and Global Illumination (Morgan Kaufmann, San Francisco, 1994).
  2. Y. O’Donnell, FrameGraph: Extensible Rendering Architecture in Frostbite.Game Developers Conference. 2017.
    https://www.gdcvault.com/play/1024612/FrameGraph-Extensible-Rendering-Architecture-in . Cited March 5, 2025.
  3. G. Wihlidal, Halcyon: Rapid Innovation Using Modern Graphics.
    https://media.contentapi.ea.com/content/dam/ea/seed/presentations/wihlidal2019-rebootdevelopblue-halcyon-rapid-innovation.pdf . Cited March 5, 2025.
  4. R. Sandu and A. Shcherbakov, “A Resource Allocation Algorithm for a History-Aware Frame Graph,” J. WSCG 31 (1-2), 63-70 (2023).
    doi 10.24132/jwscg.2023.7
  5. R. Sandu and A. Shcherbakov, “GPU Cache Flush Minimization in Render Graph Systems,” J. WSCG 32 (1-2), 71-78 (2024).
    doi 10.24132/jwscg.2024.8
  6. Using Resource Barriers to Synchronize Resource States in Direct3D 12.
    https://learn.microsoft.com/en-us/windows/win32/direct3d12/using-resource-barriers-to-synchronize-resource-states-in-direct3d-12 . Cited March 5, 2025.
  7. Understanding Vulkan Synchronization.
    https://www.khronos.org/blog/understanding-vulkan-synchronization . Cited March 5, 2025.
  8. memoryBarrier(scope: after: before: ).
    https://developer.apple.com/documentation/metal/mtlrendercommandencoder/memorybarrier(scope: after: before: ). Cited March 5, 2025.
  9. C. Wyman, S. Hargreaves, P. Shirley, and C. Barré-Brisebois, Introduction to DirectX RayTracing. 2018.
    https://intro-to-dxr.cwyman.org/. Cited March 5, 2025.
  10. M. Stich, Introduction to NVIDIA RTX and DirectX Ray Tracing. 2018.
    https://developer.nvidia.com/blog/introduction-nvidia-rtx-directx-ray-tracing/. Cited March 5, 2025.
  11. C. Crassin, F. Neyret, M. Sainz, et al., Interactive Indirect Illumination Using Voxel Cone Tracing: A Preview. 2011.
    doi 10.1145/1944745.1944787
  12. T. Ritschel, T. Grosch, and H.-P. Seidel, “Approximating Dynamic Global Illumination in Image Space,” 2009.
    doi 10.1145/1507149.1507161
  13. J. Jimenez, X.-Ch. Wu, A. Pesce, et al., Practical Real-Time Strategies for Accurate Indirect Occlusion. 2016.
    https://www.activision.com/cdn/research/Practical_Real_Time_Strategies_for_Accurate_Indirect_Occlusion_NEW Cited March 5, 2025.
  14. A. Marrs, RTXGI: Scalable Ray Traced Global Illumination in Real Time. 2020.
    https://developer.download.nvidia.com/rtx/rtxgi/NVIDIA-RTXGI-03-23-2020-v2.pdf . Cited March 6, 2025.
  15. M. McGuire, Dynamic Diffuse Global Illumination. 2019.
    https://morgan3d.github.io/articles/2019-04-01-ddgi/. Cited March 6, 2025.
  16. Quake Lightmaps. 2015.
    https://jbush001.github.io/2015/06/11/quake-lightmaps.html . Cited March 6, 2025.
  17. R. Green, Spherical Harmonic Lighting: The Gritty Details. 2003.
    https://3dvar.com/Green2003Spherical.pdf . Cited March 6, 2025.
  18. B. Kahl, Hardware Acceleration of Progressive Refinement Radiosity Using Nvidia RTX. 2023.
    https://arxiv.org/abs/2303.14831 . Cited March 6, 2025.
  19. A. Shcherbakov, V. Frolov, and V. Galaktionov, “Virtual Patches Approach for Radiosity,” Proceedings of ISP RAS 34 (3), 47-60 (2022).
    doi 10.15514/ISPRAS-2022-34(3)-4
  20. P. Hanrahan, D. Salzman, and L. Aupperle, “A Rapid Hierarchical Radiosity Algorithm,” Comput. Graph. 25 (4), 197-206 (1991).
  21. C. Damez and F. X. Sillion, “Space-Time Hierarchical Radiosity,” 1999.
    https://inria.hal.science/inria-00527746/file/SpaceTimeRad.pdf . Cited March 6, 2025.
  22. A. S. Shcherbakov and V. A. Frolov, “Matrix Transformations for Effective Implementation of Radiosity Algorithm Using Graphic Processors,” Svetotekhnika, No. 3, 43-47 (2018) [Light Eng. 27 (2), 105-110 (2019)].
    doi 10.33383/2017-081
  23. A. Shcherbakov and V. Frolov, “Dynamic Radiosity,” Computer Science Research Notes (2019), pp. 83-90.
    doi 10.24132/CSRN.2019.2901.1.10
  24. A. S. Shcherbakov, V. A. Frolov, and V. A. Galaktionov, Temporal Radiosity Method for 3D-Scenes of Arbitrary Detailization , Preprint No. 76 (Keldysh Institute of Applied Mathematics, Moscow, 2023).
    doi 10.20948/prepr-2023-76
  25. A. J. Walker, “New Fast Method for Generating Discrete Random Numbers with Arbitrary Frequency Distributions,” Electronics Lett. 10 (8), 127-128 (1974).
    doi 10.1049/el: 19740097.
  26. L. Yang, S. Liu, and M. Salvi, “A Survey of Temporal Antialiasing Techniques,” Comput. Graph. Forum 39 (2), 607-621 (2020).
    doi 10.1111/cgf.14018
  27. Temporal Super Resolution.
    https://docs.unrealengine.com/5.2/en-US/temporal-super-resolution-in-unreal-engine/. Cited March 6, 2025.
  28. H.-P. Lehmann, L. Hübschle-Schneider, and P. Sanders, “Weighted Random Sampling on GPUs,” 2021.
    https://arxiv.org/abs/2106.12270 . Cited March 6, 2025.

License

Copyright (c) 2025 А. С. Щербаков

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.