Detecting Aliasing Artifacts in Image Sequences Using Deep Neural Networks

Simple item page
dc.contributor.authorPatney, Anjulen_US
dc.contributor.authorLefohn, Aaronen_US
dc.contributor.editorPatney, Anjul and Niessner, Matthiasen_US
dc.date.accessioned2018-11-11T10:45:59Z
dc.date.available2018-11-11T10:45:59Z
dc.date.issued2018
dc.description.abstractIn 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.en_US
dc.description.sectionheadersAnti Aliasing
dc.description.seriesinformationEurographics/ ACM SIGGRAPH Symposium on High Performance Graphics
dc.identifier.doi10.1145/3231578.3231580
dc.identifier.isbn978-1-4503-5896-5
dc.identifier.issn2079-8679
dc.identifier.urihttps://doi.org/10.1145/3231578.3231580
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1145/3231578-3231580
dc.publisherACMen_US
dc.subjectComputing methodologies
dc.subjectAntialiasing
dc.subjectMachine learning
dc.subjectaliasing
dc.subjectvisual quality assessment
dc.subjectmachine learning
dc.titleDetecting Aliasing Artifacts in Image Sequences Using Deep Neural Networksen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
04-1010-patney.pdf
Size:
17.52 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
04-1010.mp4
Size:
158.67 MB
Format:
Unknown data format
Download
Collections
High-Performance Graphics 2018