Detecting Aliasing Artifacts in Image Sequences Using Deep Neural Networks

Patney, Anjul; Lefohn, Aaron

Detecting Aliasing Artifacts in Image Sequences Using Deep Neural Networks

Files

04-1010-patney.pdf (17.52 MB)

04-1010.mp4 (158.67 MB)

Date

2018

Authors

Patney, Anjul
Lefohn, Aaron

Publisher

ACM

Abstract

In this short paper we present a machine learning approach to detect visual artifacts in rendered image sequences. Specifically, we train a deep neural network using example aliased and antialiased image sequences exported from a real-time renderer. The trained network learns to identify and locate aliasing artifacts in an input sequence, without comparing it against a ground truth. Thus, it is useful as a fully automated tool for evaluating image quality. We demonstrate the effectiveness of our approach in detecting aliasing in several rendered sequences. The trained network correctly predicts aliasing in 64×64×4 animated sequences with more than 90% accuracy for images it hasn't seen before. The output of our network is a single scalar between 0 and 1, which is usable as a quality metric for aliasing. It follows the same trend as (1-SSIM) for images with increasing sample counts.

        @inproceedings{10.1145:3231578.3231580
,
booktitle = {Eurographics/ ACM SIGGRAPH Symposium on High Performance Graphics
},
editor = {Patney, Anjul and Niessner, Matthias
},
title = {{Detecting Aliasing Artifacts in Image Sequences Using Deep Neural Networks
}},
author = {Patney, Anjul and 
Lefohn, Aaron
},
year = {2018
},
publisher = {ACM
},
ISSN = {2079-8679
},
ISBN = {978-1-4503-5896-5
},
DOI = {10.1145/3231578.3231580
}
}