Real-time Monte Carlo Denoising with Weight Sharing Kernel Prediction Network
| dc.contributor.author | Fan, Hangming | en_US |
| dc.contributor.author | Wang, Rui | en_US |
| dc.contributor.author | Huo, Yuchi | en_US |
| dc.contributor.author | Bao, Hujun | en_US |
| dc.contributor.editor | Bousseau, Adrien and McGuire, Morgan | en_US |
| dc.date.accessioned | 2021-07-12T12:08:51Z | |
| dc.date.available | 2021-07-12T12:08:51Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | Real-time Monte Carlo denoising aims at removing severe noise under low samples per pixel (spp) in a strict time budget. Recently, kernel-prediction methods use a neural network to predict each pixel's filtering kernel and have shown a great potential to remove Monte Carlo noise. However, the heavy computation overhead blocks these methods from real-time applications. This paper expands the kernel-prediction method and proposes a novel approach to denoise very low spp (e.g., 1-spp) Monte Carlo path traced images at real-time frame rates. Instead of using the neural network to directly predict the kernel map, i.e., the complete weights of each per-pixel filtering kernel, we predict an encoding of the kernel map, followed by a high-efficiency decoder with unfolding operations for a high-quality reconstruction of the filtering kernels . The kernel map encoding yields a compact single-channel representation of the kernel map, which can significantly reduce the kernel-prediction network's throughput. In addition, we adopt a scalable kernel fusion module to improve denoising quality. The proposed approach preserves kernel prediction methods' denoising quality while roughly halving its denoising time for 1-spp noisy inputs. In addition, compared with the recent neural bilateral grid-based real-time denoiser, our approach benefits from the high parallelism of kernel-based reconstruction and produces better denoising results at equal time. | en_US |
| dc.description.number | 4 | |
| dc.description.sectionheaders | Denoising | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 40 | |
| dc.identifier.doi | 10.1111/cgf.14338 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 15-27 | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.14338 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf14338 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | Computing methodologies --> Neural networks | |
| dc.subject | Ray tracing | |
| dc.title | Real-time Monte Carlo Denoising with Weight Sharing Kernel Prediction Network | en_US |