Deep Volumetric Ambient Occlusion

TL;DR

This paper introduces a deep learning method called DVAO for real-time volumetric ambient occlusion in volume rendering, effectively predicting global illumination effects interactively across different data modalities.

Contribution

It presents a novel neural network approach for volumetric ambient occlusion that supports real-time interaction and generalizes across modalities, with analysis of transfer function strategies.

Findings

DVAO achieves accurate ambient occlusion predictions in volume rendering.

The method supports real-time interaction by updating only on transfer function changes.

DVAO generalizes well to modalities beyond training data.

Abstract

We present a novel deep learning based technique for volumetric ambient occlusion in the context of direct volume rendering. Our proposed Deep Volumetric Ambient Occlusion (DVAO) approach can predict per-voxel ambient occlusion in volumetric data sets, while considering global information provided through the transfer function. The proposed neural network only needs to be executed upon change of this global information, and thus supports real-time volume interaction. Accordingly, we demonstrate DVAOs ability to predict volumetric ambient occlusion, such that it can be applied interactively within direct volume rendering. To achieve the best possible results, we propose and analyze a variety of transfer function representations and injection strategies for deep neural networks. Based on the obtained results we also give recommendations applicable in similar volume learning scenarios. Lastly, we show that DVAO generalizes to a variety of modalities, despite being trained on computed tomography data only.