Deep Volumetric Ambient Occlusion

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.

arXiv commentIEEE VIS SciVis 2020

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Conditional Generative Adversarial Nets
• Deep learning for time series classification: a review
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Mixed Precision Training
• On the Variance of the Adaptive Learning Rate and Beyond
• Lookahead Optimizer: k steps forward, 1 step back
• Deep Shading: Convolutional Neural Networks for Screen-Space Shading
• A Generative Model for Volume Rendering
• Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans
• Volumetric Isosurface Rendering with Deep Learning-Based Super-Resolution
• Inviwo -- A Visualization System with Usage Abstraction Levels

Cited by in corpus (4)

• Exploratory Lagrangian-Based Particle Tracing Using Deep Learning
• Deep Direct Volume Rendering: Learning Visual Feature Mappings From Exemplary Images
• Monocular Depth Decomposition of Semi-Transparent Volume Renderings
• Three-dimensional visualization of X-ray micro-CT with large-scale datasets: Efficiency and accuracy for real-time interaction