Deep Volumetric Ambient Occlusion

Dominik Engel, Timo Ropinski

View presentation:2020-10-29T18:00:00ZGMT-0600Change your timezone on the schedule page
2020-10-29T18:00:00Z
Exemplar figure
With Deep Volumetric Ambient Occlusion we present a novel deep-learning based technique for volumetric ambient occlusion. We discuss how additional, possibly unstructured information, like the transfer function can be provided to 3D CNNs and present our takeaways for volume learning.
Fast forward

Direct link to video on YouTube: https://youtu.be/AMLlnwqGiIU

Keywords

Volume illumination, deep learning, direct volume rendering.

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 DVAO's 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.