Journal
COMPUTER GRAPHICS FORUM
Volume 40, Issue 4, Pages 15-27Publisher
WILEY
DOI: 10.1111/cgf.14338
Keywords
-
Categories
Funding
- NSFC [61872319]
- Zhejiang Provincial NSFC [LR18F020002]
- National Key R&D Program of China [2017YFB1002605]
- Zhejiang University Education Foundation Global Partnership Fund
Ask authors/readers for more resources
This paper introduces a novel real-time Monte Carlo denoising method that encodes and reconstructs the kernel map efficiently to achieve real-time denoising of very low spp images. By utilizing a scalable kernel fusion module to improve denoising quality, the proposed approach significantly reduces the throughput of the kernel-prediction network.
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.
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