Rendering photorealistic images has been a long-standing problem in computer graphics. Photorealistic image synthesis is still a vibrant and active research field with many open problems. Most offline methods use path-sampling techniques to evaluate the rendering equation to account for sophisticated light-transport effects. However, this procedure takes up to hours, where the inaccuracy of the initial estimation shows up as noise in the resulting images. In order to alleviate this, sophisticated light-transport algorithms and a number of noise-filtering techniques have been developed. Despite the fact that a large body of research exists in both directions, there are no standardized datasets that enable us to adequately assess their strengths and weaknesses. It would be of utmost importance to be able to compare existing light-transport and noise-filtering algorithms in a scientifically sound way. In this project, we will therefore create such a dataset, and provide the following contributions: (1) a set of scene descriptions that can be used to test individual features of these systems, e.g., dealing with a variety of material models, high-resolution geometry, textured inputs, and a variety of lighting effects. (2) a large number of rendered images of these scenes with different noisiness, auxiliary buffers to maximize compatibility with the state-of-the-art noise filtering algorithms, and fully converged reference images for easy comparisons against the denoised outputs, and (3) a method to ensure parameter coverage, so that the dataset does not become prohibitively large, but still covers salient rendering configurations, that reveal the most interesting cases. In summary, we propose to create a fertile ground for assessing the quality of different photorealistic rendering techniques. We believe that this would lead to significantly higher quality scientific works in the field.


  • FWF ORD 61


Research Areas

  • In this area, we concentrate on algorithms that synthesize images to depict 3D models or scenes, often by simulating or approximating the physics of light.


7 Publications found:
Image Bib Reference Publication Type
Christian Freude, Hiroyuki Sakai, Karoly Zsolnai-FehérORCID iD, Michael WimmerORCID iD
Sampling-Distribution-Based Evaluation for Monte Carlo Rendering
In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pages 119-130. 2023.
[image] [paper]
Conference Paper
Elias Brugger, Christian Freude, Michael WimmerORCID iD
Test Scene Design for Physically Based Rendering

[paper] [arXiv]
Miscellaneous Publication
Christian Freude, Hiroyuki Sakai, Karoly Zsolnai-FehérORCID iD, Michael WimmerORCID iD
R-Score: A Novel Approach to Compare Monte Carlo Renderings
TR-193-02-2020-4, August 2020 [technical-report]
Technical Report
Elias Brugger
Test Scene Design for Physically Based Rendering
Bachelor Thesis
Andreas Wiesinger
An Open Database for Physically Based Rendering
Bachelor Thesis
Error spectrum ensemble Adam Celarek, Wenzel Jakob, Michael WimmerORCID iD, Jaakko Lehtinen
Quantifying the Error of Light Transport Algorithms
Computer Graphics Forum, 38(4):111-121, July 2019. [paper_preprint] [Git repository]
Journal Paper with Conference Talk
Adam Celarek
Quantifying the Convergence of Light-Transport Algorithms
[poster] [thesis]
Master Thesis
Download list as Bibtex, HTML (Advanced, Expert), JSON (with referenced objects), CSV, Permalink


Project Leader

Start Date

End Date