Unsupervised Image Reconstruction for Gradient‐Domain Volumetric Rendering. (24th November 2020)

• Record Type: Journal Article
• Authors: Xu, Zilin; Sun, Qiang; Wang, Lu; Xu, Yanning; Wang, Beibei
• Is Part Of: Computer graphics forum. Volume 39:Number 7(2020)
• Page Start: 193
• Page End: 203
• Publication Date: 2020-11-24
• Subjects: CCS Concepts -- Computing methodologies → Neural network -- Ray tracing; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.14137
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: Gradient‐domain rendering can highly improve the convergence of light transport simulation using the smoothness in image space. These methods generate image gradients and solve an image reconstruction problem with rendered image and the gradient images. Recently, a previous work proposed a gradient‐domain volumetric photon density estimation for homogeneous participating media. However, the image reconstruction relies on traditional L1 reconstruction, which leads to obvious artifacts when only a few rendering passes are performed. Deep learning based reconstruction methods have been exploited for surface rendering, but they are not suitable for volume density estimation. In this paper, we propose an unsupervised neural network for image reconstruction of gradient‐domain volumetric photon density estimation, more specifically for volumetric photon mapping, using a variant of GradNet with an encoded shift connection and a separated auxiliary feature branch, which includes volume based auxiliary features such as transmittance and photon density. Our network smooths the images on global scale and preserves the high frequency details on a small scale. We demonstrate that our network produces a higher quality result, compared to previous work. Although we only considered volumetric photon mapping, it's straightforward to extend our method for other forms, like beam radiance estimation.