Publikationen

Deep Volumetric Ambient Occlusion

Deep Volumetric Ambient Occlusion

Dominik Engel Ulm University Timo Ropinski Ulm University

IEEE Transactions on Visualization and Computer Graphics (Proc. of IEEE Scientific Visualisation Conference 2020), 2020

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.

Video

Bibtex

content_copy
@article{engel2020deep,
	title={Deep Volumetric Ambient Occlusion},
	author={Engel, Dominik and Ropinski, Timo},
	year={2020},
	month={0},
	journal={IEEE Transactions on Visualization and Computer Graphics (Proc. of IEEE Scientific Visualisation Conference (2020))},
	volume={27},
	pages={1268-1278},
	issue={2},
	doi={10.1109/TVCG.2020.3030344}
}