# DEMC: A Deep Dual-Encoder Network for Denoising Monte Carlo Rendering

## TL;DR

DEMC introduces a deep dual-encoder network that effectively denoises Monte Carlo rendered images by leveraging feature buffers, achieving faster and more robust results compared to existing methods.

## Contribution

The paper proposes a novel dual-encoder network with feature fusion for efficient Monte Carlo denoising, improving robustness and speed over prior approaches.

## Key findings

- Outperforms state-of-the-art denoising methods in quality.
- Operates significantly faster than existing techniques.
- Maintains detail preservation across diverse scenes.

## Abstract

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.