Ambient Occlusion Baking via a Feed-Forward Neural Network
| dc.contributor.author | Erra, Ugo | en_US |
| dc.contributor.author | Capece, Nicola Felice | en_US |
| dc.contributor.author | Agatiello, Roberto | en_US |
| dc.contributor.editor | Adrien Peytavie and Carles Bosch | en_US |
| dc.date.accessioned | 2017-04-22T16:46:58Z | |
| dc.date.available | 2017-04-22T16:46:58Z | |
| dc.date.issued | 2017 | |
| dc.description.abstract | We present a feed-forward neural network approach for ambient occlusion baking in real-time rendering. The idea is based on implementing a multi-layer perceptron that allows a general encoding via regression and an efficient decoding via a simple GPU fragment shader. The non-linear nature of multi-layer perceptrons makes them suitable and effective for capturing nonlinearities described by ambient occlusion values. A multi-layer perceptron is also random-accessible, has a compact size, and can be evaluated efficiently on the GPU. We illustrate our approach of screen-space ambient occlusion based on neural network including its quality, size, and run-time speed. | en_US |
| dc.description.sectionheaders | Lighting and Rendering | |
| dc.description.seriesinformation | EG 2017 - Short Papers | |
| dc.identifier.doi | 10.2312/egsh.20171003 | |
| dc.identifier.issn | 1017-4656 | |
| dc.identifier.pages | 13-16 | |
| dc.identifier.uri | https://doi.org/10.2312/egsh.20171003 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/egsh20171003 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.subject | I.3.3 [Picture/Image Generation] | |
| dc.subject | Display Algorithms | |
| dc.subject | I.3.7 [Three Dimensional Graphics and Realism] | |
| dc.subject | Color | |
| dc.subject | shading | |
| dc.subject | shadowing | |
| dc.subject | and texture | |
| dc.title | Ambient Occlusion Baking via a Feed-Forward Neural Network | en_US |