Perceptually inspired real-time artistic style transfer for video stream
Authors: Kang, D., Tian, F. and Seo, S.
Journal: Journal of Real-Time Image Processing
Volume: 13
Issue: 3
Pages: 581-589
ISSN: 1861-8200
DOI: 10.1007/s11554-016-0612-0
Abstract:This study presents a real-time texture transfer method for artistic style transfer for video stream. We propose a parallel framework using a T-shaped kernel to enhance the computational performance. With regard to accelerated motion estimation, which is necessarily required for maintaining temporal coherence, we present a method using a downscaled motion field to successfully achieve high real-time performance for texture transfer of video stream. In addition, to enhance the artistic quality, we calculate the level of abstraction using visual saliency and integrate it with the texture transfer algorithm. Thus, our algorithm can stylize video with perceptual enhancements.
https://eprints.bournemouth.ac.uk/24358/
Source: Scopus
Perceptually inspired real-time artistic style transfer for video stream
Authors: Kang, D., Tian, F. and Seo, S.
Journal: JOURNAL OF REAL-TIME IMAGE PROCESSING
Volume: 13
Issue: 3
Pages: 581-589
eISSN: 1861-8219
ISSN: 1861-8200
DOI: 10.1007/s11554-016-0612-0
https://eprints.bournemouth.ac.uk/24358/
Source: Web of Science (Lite)
Perceptually Inspired Real-time Artistic Style Transfer for Video Stream
Authors: Kang, D.W., Tian, F. and Seo, S.H.
Journal: Journal of Real-Time Image Processing
Publisher: Springer Berlin Heidelberg
ISSN: 1861-8219
DOI: 10.1007/s11554-016-0612-0
Abstract:This study presents a real-time texture transfer method for artistic style transfer for video stream. We propose a parallel framework using a T-shaped kernel to enhance the computational performance. With regard to accelerated motion estimation, which is necessarily required for maintaining temporal coherence, we present a method using a downscaled motion field to successfully achieve high real-time performance for texture transfer of video stream. In addition, to enhance the artistic quality, we calculate the level of abstraction using visual saliency and integrate it with the texture transfer algorithm. Thus, our algorithm can stylize video with perceptual enhancements.
https://eprints.bournemouth.ac.uk/24358/
Source: Manual
Perceptually Inspired Real-time Artistic Style Transfer for Video Stream
Authors: Kang, D., Tian, F. and Seo, S.H.
Journal: Journal of Real-Time Image Processing
Volume: 13
Issue: 3
Pages: 581-589
ISSN: 1861-8219
Abstract:This study presents a real-time texture transfer method for artistic style transfer for video stream. We propose a parallel framework using a T-shaped kernel to enhance the computational performance. With regard to accelerated motion estimation, which is necessarily required for maintaining temporal coherence, we present a method using a downscaled motion field to successfully achieve high real-time performance for texture transfer of video stream. In addition, to enhance the artistic quality, we calculate the level of abstraction using visual saliency and integrate it with the texture transfer algorithm. Thus, our algorithm can stylize video with perceptual enhancements.
https://eprints.bournemouth.ac.uk/24358/
Source: BURO EPrints