Ambient Occlusion Baking via a Feed-Forward Neural Network

Erra, Ugo; Capece, Nicola Felice; Agatiello, Roberto

Ambient Occlusion Baking via a Feed-Forward Neural Network

Files

013-016.pdf (940.29 KB)

ao_baking_via_neural_network.zip (51.52 MB)

neuralnetwork.mp4 (89.95 MB)

Date

2017

Authors

Erra, Ugo
Capece, Nicola Felice
Agatiello, Roberto

Publisher

The Eurographics Association

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.

        @inproceedings{10.2312:egsh.20171003
,
booktitle = {EG 2017 - Short Papers
},
editor = {Adrien Peytavie and Carles Bosch
},
title = {{Ambient Occlusion Baking via a Feed-Forward Neural Network
}},
author = {Erra, Ugo and 
Capece, Nicola Felice and 
Agatiello, Roberto
},
year = {2017
},
publisher = {The Eurographics Association
},
ISSN = {1017-4656
},
ISBN = {},
DOI = {10.2312/egsh.20171003
}
}