DEMC: A Deep Dual-Encoder Network for Denoising Monte Carlo Rendering
This addresses denoising for Monte Carlo rendering in computer graphics, which is incremental as it builds on existing feature buffer approaches.
The paper tackles the problem of removing Monte Carlo noise in rendering while preserving details, proposing DEMC, a deep Dual-Encoder network that fuses feature buffers and noisy images to reconstruct clean images. The result is a model that is more robust across scenes and significantly faster than state-of-the-art methods.
In this paper, we present DEMC, a deep Dual-Encoder network to remove Monte Carlo noise efficiently while preserving details. Denoising Monte Carlo rendering is different from natural image denoising since inexpensive by-products (feature buffers) can be extracted in the rendering stage. Most of them are noise-free and can provide sufficient details for image reconstruction. However, these feature buffers also contain redundant information, which makes Monte Carlo denoising different from natural image denoising. Hence, the main challenge of this topic is how to extract useful information and reconstruct clean images. To address this problem, we propose a novel network structure, Dual-Encoder network with a feature fusion sub-network, to fuse feature buffers firstly, then encode the fused feature buffers and a noisy image simultaneously, and finally reconstruct a clean image by a decoder network. Compared with the state-of-the-art methods, our model is more robust on a wide range of scenes and is able to generate satisfactory results in a significantly faster way.