Sampling-Distribution-Based Evaluation for Monte Carlo Rendering

Information

• Publication Type: Conference Paper
• Workgroup(s)/Project(s):
  • A Test Suite for Photorealistic Rendering and Filtering
  • Advanced Computational Design
• Date: 2023
• ISBN: 978-989-758-634-7
• Publisher: Scitepress
• Open Access: yes
• Location: Lisbon, Portugal
• Lecturer: Christian Freude
• Event: 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (GRAPP)
• DOI: 10.5220/0011886300003417
• Booktitle: Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
• Pages: 12
• Volume: 1
• Conference date: 19. February 2023 – 21. February 2023
• Pages: 119 – 130
• Keywords: computer graphics, Rendering, Ray Tracing, Evaluation, Validation

Abstract

In this paper, we investigate the application of per-pixel difference metrics for evaluating Monte Carlo (MC) rendering techniques. In particular, we propose to take the sampling distribution of the mean (SDM) into account for this purpose. We establish the theoretical background and analyze other per-pixel difference metrics, such as the absolute deviation (AD) and the mean squared error (MSE) in relation to the SDM. Based on insights from this analysis, we propose a new, alternative, and particularly easy-to-use approach, which builds on the SDM and facilitates meaningful comparisons of MC rendering techniques on a per-pixel basis. In order to demonstrate the usefulness of our approach, we compare it to commonly used metrics based on a variety of images computed with different rendering techniques. Our evaluation reveals limitations of commonly used metrics, in particular regarding the detection of differences between renderings that might be difficult to detect otherwise—this circ umstance is particularly apparent in comparison to the MSE calculated for each pixel. Our results indicate the potential of SDM-based approaches to reveal differences between MC renderers that might be caused by conceptual or implementation-related issues. Thus, we understand our approach as a way to facilitate the development and evaluation of rendering techniques.

Additional Files and Images

Weblinks

• Entry in reposiTUm (TU Wien Publication Database)
• DOI: 10.5220/0011886300003417

BibTeX

@inproceedings{freude-2023-sem,
  title =      "Sampling-Distribution-Based Evaluation for Monte Carlo
               Rendering",
  author =     "Christian Freude and Hiroyuki Sakai and Karoly
               Zsolnai-Feh\'{e}r and Michael Wimmer",
  year =       "2023",
  abstract =   "In this paper, we investigate the application of per-pixel
               difference metrics for evaluating Monte Carlo (MC) rendering
               techniques. In particular, we propose to take the sampling
               distribution of the mean (SDM) into account for this
               purpose. We establish the theoretical background and analyze
               other per-pixel difference metrics, such as the absolute
               deviation (AD) and the mean squared error (MSE) in relation
               to the SDM. Based on insights from this analysis, we propose
               a new, alternative, and particularly easy-to-use approach,
               which builds on the SDM and facilitates meaningful
               comparisons of MC rendering techniques on a per-pixel basis.
               In order to demonstrate the usefulness of our approach, we
               compare it to commonly used metrics based on a variety of
               images computed with different rendering techniques. Our
               evaluation reveals limitations of commonly used metrics, in
               particular regarding the detection of differences between
               renderings that might be difficult to detect
               otherwise—this circ umstance is particularly apparent in
               comparison to the MSE calculated for each pixel. Our results
               indicate the potential of SDM-based approaches to reveal
               differences between MC renderers that might be caused by
               conceptual or implementation-related issues. Thus, we
               understand our approach as a way to facilitate the
               development and evaluation of rendering techniques.",
  isbn =       "978-989-758-634-7",
  publisher =  "Scitepress",
  location =   "Lisbon, Portugal",
  event =      "18th International Joint Conference on Computer Vision,
               Imaging and Computer Graphics Theory and Applications
               (GRAPP)",
  doi =        "10.5220/0011886300003417",
  booktitle =  "Proceedings of the 18th International Joint Conference on
               Computer Vision, Imaging and Computer Graphics Theory and
               Applications",
  pages =      "12",
  volume =     "1",
  pages =      "119--130",
  keywords =   "computer graphics, Rendering, Ray Tracing, Evaluation,
               Validation",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2023/freude-2023-sem/",
}