Dataset and Code for Progressive Denoising of Monte Carlo Rendered Images

DOI10.5281/zenodo.10057326Zenodo10057326MaRDI QIDQ6695270

Dataset published at Zenodo repository.

Author name not available (Why is that?)

Dataset and code for the journal article Progressive Denoising of Monte Carlo Rendered Images, published in Computer Graphics Forum 41, 2 (May 2022), 1–11 (https://doi.org/10.1111/cgf.14454). Cite the journal article, when used in a publication:@inproceedings{firmino2022progressive, title={Progressive Denoising of Monte Carlo Rendered Images}, author={Firmino, Arthur and Frisvad, Jeppe Revall and Jensen, Henrik Wann}, booktitle={Computer Graphics Forum}, volume={41}, number={2}, pages={1--11}, year={2022}, organization={Wiley Online Library} }Dataset contains images in multi-channel EXR format used in the training, validation, and testing of the progressive denoising models trained as part of the publication (also attached). If using the attached code, execute the command, "git submodule update --init --recursive" in the unzipped folder to pull the required dependencies, and see the README.md file for additional instructions.Abstract: Image denoising based on deep learning has become a powerful tool to accelerate Monte Carlo rendering. Deep learning techniques can produce smooth images using a low sample count. Unfortunately, existing deep learning methods are biased and do not converge to the correct solution as the number of samples increase. In this paper, we propose a progressive denoising technique that aims to use denoising only when it is beneficial and to reduce its impact at high sample counts. We use Stein's unbiased risk estimate (SURE) to estimate the error in the denoised image, and we combine this with a neural network to infer a per-pixel mixing parameter. We further augment this network with confidence intervals based on classical statistics to ensure consistency and convergence of the final denoised image. Our results demonstrate that our method is consistent and that it improves existing denoising techniques. Furthermore, it can be used in combination with existing high quality denoisers to ensure consistency. In addition to being asymptotically unbiased, progressive denoising is particularly good at preserving fine details that would otherwise be lost with existing denoisers.

This page was built for dataset: Dataset and Code for Progressive Denoising of Monte Carlo Rendered Images