English

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

Multimedia 2021-03-29 v2 Graphics

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.

Keywords

Cite

@article{arxiv.1905.03908,
  title  = {DEMC: A Deep Dual-Encoder Network for Denoising Monte Carlo Rendering},
  author = {Xin Yang and Wenbo Hu and Dawei Wang and Lijing Zhao and Baocai Yin and Qiang Zhang and Xiaopeng Wei and Hongbo Fu},
  journal= {arXiv preprint arXiv:1905.03908},
  year   = {2021}
}

Comments

Published in Journal of Computer Science and Technology. The final publication is available at springerlink.com

R2 v1 2026-06-23T09:02:21.265Z