Journal
COMPUTER GRAPHICS FORUM
Volume 40, Issue 1, Pages 369-381Publisher
WILEY
DOI: 10.1111/cgf.14194
Keywords
deep learning; Monte Carlo denoising; path-based; sample-based; neural network
Categories
Funding
- National Key R&D Program of China [2017YFB0203000]
- National Natural Science Foundation of China [61802187, 61872223]
- Fundamental Research Funds for the Central Universities [30920021133]
- China Postdoctoral Science Foundation [2020M671500]
- Jiangsu Postdoctoral Science Foundation [2020Z165]
Ask authors/readers for more resources
This paper introduces a new technique using deep learning methods for denoising in Monte Carlo rendering. By handling three scales of features, using an improved feature extractor, and feature attention mechanism, it achieves higher quality denoising results and better preservation of details compared to previous methods.
Monte Carlo rendering is widely used in the movie industry. Since it is costly to produce noise-free results directly, Monte Carlo denoising is often applied as a post-process. Recently, deep learning methods have been successfully leveraged in Monte Carlo denoising. They are able to produce high quality denoised results, even with very low sample rate, e.g. 4 spp (sample per pixel). However, for difficult scene configurations, some details could be blurred in the denoised results. In this paper, we aim at preserving more details from inputs rendered with low spp. We propose a novel denoising pipeline that handles three-scale features - pixel, sample and path - to preserve sharp details, uses an improved Res2Net feature extractor to reduce the network parameters and a smooth feature attention mechanism to remove low-frequency splotches. As a result, our method achieves higher denoising quality and preserves better details than the previous methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available