Jonas Deyson B. Santos1 jdbsantos@inf.ufrgs.br |
Pradeep Sen2 psen@ece.ucsb.edu |
Manuel M. Oliveira1 oliveira@inf.ufrgs.br |
The Visual Computer.
Volume 34, Number 6-8, June 2018, pp. 765-778. [DOI]
Abstract | Downloads | Video | Reference | Acknowledgments |
Although many adaptive sampling and reconstruction techniques have been proposed in the last few years, the case for which one should be used for a specific scene is still to be made. Moreover, developing a new technique has required selecting a particular rendering system, which makes the technique tightly coupled to the chosen renderer and limits the amount of scenes it can be tested on. In this paper, we propose a renderer-agnostic framework for testing and benchmarking sampling and denoising techniques for Monte Carlo rendering. It decouples techniques from rendering systems by hiding the renderer details behind an API. This improves productivity and allows for direct comparisons among techniques originally developed for different rendering systems. We demonstrate its effectiveness by using our API to instrument four rendering systems and most state-of-the-art Monte Carlo denoising techniques, and performing a benchmark across rendering systems.
Notice: This is the author's version of the work. The definitive version was published by Springer TVCJ, Vol. 34, Issue 6-8, June 2018, pp. 765-778 — https://doi.org/10.1007/s00371-018-1521-y,.
Santos, J. D. B., Sen, P., Oliveira, M. M. 2018. "A Framework for Developing and Benchmarking Sampling and Denoising Algorithms for Monte Carlo Rendering" The Visual Computer. Volume 34 (2018), Issue 6-8, pp. 765--778.
@article{Santos:2018:FBKSD,
author = {Jonas Deyson B. Santos and Pradeep Sen and Manuel M. Oliveira},
title = {A Framework for Developing and Benchmarking Sampling and Denoising Algorithms for Monte Carlo Rendering},
journal = {The Visual Computer},
volume = {34},
issue = {6-8},
year = {2018},
pages = {765--778},
doi = {10.1007/s00371-018-1521-y}
issn = {0178-2789}}
Monte Carlo Rendering, Adaptive Sampling and Reconstruction, Denoising, Benchmark.
CAPES | |
CNPq-Brazil fellowships and grants 306196/2014-0, 423673/2016-5. | |
NSF grants IIS-1321168 and IIS-1619376. |