DGAN-KPN: Deep Generative Adversarial Network and Kernel Prediction Network for Denoising MC Renderings

Abstract

In this paper, we present a denoising network composed of a kernel prediction network and a deep generative adversarial network to construct an end-to-end overall network structure. The network structure consists of three parts: the Kernel Prediction Network (KPN), the Deep Generation Adversarial Network (DGAN), and the image reconstruction model. The kernel prediction network model takes the auxiliary feature information image as the input, passes through the source information encoder, the feature information encoder, and the kernel predictor, and finally generates a prediction kernel for each pixel. The generated adversarial network model is divided into two parts: the generator model and the multiscale discriminator model. The generator model takes the noisy Monte Carlo-rendered image as the input, passes through the symmetric encoder–decoder structure and the residual block structure, and finally outputs the rendered image with preliminary denoising. Then, the prediction kernel and the preliminarily denoised rendered image is sent to the image reconstruction model for reconstruction, and the prediction kernel is applied to the preliminarily denoised rendered image to obtain a preliminarily reconstructed result image. To further improve the quality of the result and to be more robust, the initially reconstructed rendered image undergoes four iterations of filtering for further denoising. Finally, after four iterations of the image reconstruction model, the final denoised image is presented as the output. This denoised image is applied to the loss function. We compared the results from our approach with state-of-the-art results by using the structural similarity index (SSIM) values and peak signal-to-noise ratio (PSNR) values, and we reported a better performance.