Denoising Monte Carlo renderings via a multi-scale featured dual-residual GAN

Monte Carlo (MC) path tracing causes a lot of noise on the rendered image at a low samples per pixel. Recently, with the help of inexpensive auxiliary buffers and the generative adversarial network (GAN), deep learning-based denoising MC rendering methods have been able to generate noise-free images with high perceptual quality in seconds. In this paper, we propose a novel GAN structure for denoising Monte Carlo renderings, called dual residual connection GAN. Our key insight is that the dual residual connections can improve the chance of the optimal feature selection and implicitly increase the number of potential interactions between modules. We also propose a multi-scale auxiliary features extraction method, aiming to make full use of the rich geometry and texture information of auxiliary buffers. Moreover, we adopt a spatial-adaptive block with the deformable convolution to help the network adapt to the variance in spatial texture and edge features. Compared with the state-of-the-art methods, our network has fewer parameters and less inference time, and the results surpass the previous in terms of visual effects and quantitative metrics.

Automated summary

The paper proposes a novel GAN structure for denoising Monte Carlo renderings by utilizing dual residual connections and multi-scale auxiliary features extraction method. By employing spatial-adaptive blocks with deformable convolution, the network adapts to spatial texture and edge features variance, achieving better visual effects and quantitative metrics compared to previous methods.