Neural Denoising for Path Tracing of Medical Volumetric Data

Hofmann N, Martschinke J, Engel K, Stamminger M (2020)

Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 2020

Journal

Proceedings of the ACM on Computer Graphics and Interactive Techniques Association for Computing Machinery (ACM)

Book Volume: 3

Article Number: 13

Conference Proceedings Title: Proceedings of the ACM on Computer Graphics and Interactive Techniques

Event location: Online

Journal Issue: 2

URI: https://www.lgdv.tf.fau.de/?p=2278

DOI: 10.1145/3406181

Abstract

In this paper, we transfer machine learning techniques previously applied to denoising surface-only Monte Carlo renderings to path-traced visualizations of medical volumetric data. In the domain of medical imaging, path-traced videos turned out to be an efficient means to visualize and understand internal structures, in particular for less experienced viewers such as students or patients. However, the computational demands for the rendering of high-quality path-traced videos are very high due to the large number of samples necessary for each pixel. To accelerate the process, we present a learning-based technique for denoising path-traced videos of volumetric data by increasing the sample count per pixel; both through spatial (integrating neighboring samples) and temporal filtering (reusing samples over time). Our approach uses a set of additional features and a loss function both specifically designed for the volumetric case. Furthermore, we present a novel network architecture tailored for our purpose, and introduce reprojection of samples to improve temporal stability and reuse samples over frames. As a result, we achieve good image quality even from severely undersampled input images, as visible in the teaser image.

Authors with CRIS profile

Nikolai Hofmann Chair of Visual Computing Jana Martschinke Professur für Visual Computing Marc Stamminger Chair of Visual Computing

Involved external institutions

Siemens Healthineers DE Germany (DE)

How to cite

APA:

Hofmann, N., Martschinke, J., Engel, K., & Stamminger, M. (2020). Neural Denoising for Path Tracing of Medical Volumetric Data. In ACM (Eds.), Proceedings of the ACM on Computer Graphics and Interactive Techniques. Online.

MLA:

Hofmann, Nikolai, et al. "Neural Denoising for Path Tracing of Medical Volumetric Data." Proceedings of the High-Performance Graphics 2020, Online Ed. ACM, 2020.

BibTeX: Download