GANST: Gradient-aware Arbitrary Neural Style Transfer

Simple item page
dc.contributor.authorZhu, Haichaoen_US
dc.contributor.editorLee, Sung-Hee and Zollmann, Stefanie and Okabe, Makoto and Wünsche, Burkharden_US
dc.date.accessioned2021-10-14T10:05:49Z
dc.date.available2021-10-14T10:05:49Z
dc.date.issued2021
dc.description.abstractArtistic style transfer synthesizes a stylized image with content from a target image and style from an art image. The latest neural style transfer leverages texture distributions as style information, and applies the style to content images afterwards. These methods are promising; however, they could introduce semantic content loss into synthesized results inevitably with the disregarded gradient information of input images. To tackle this problem, we propose a novel gradient-aware technique, called GANST. First, GANST decomposes input images to intermediate steerable representation that capture gradient information at multiple scales based on a Steerable Pyramid Neural Network (SPNN). With the extracted information, GANST preserves semantic content by integrating a novel loss representation of local gradients to AdaIN architecture, which we call Steerable Style Transfer Network (SSTN). Experimental results on various images demonstrate that our proposed GANST outperforms the state-of-the-art methods in producing results with concrete style reflected and detailed content preserved.en_US
dc.description.sectionheadersImage Processing and Synthesis
dc.description.seriesinformationPacific Graphics Short Papers, Posters, and Work-in-Progress Papers
dc.identifier.doi10.2312/pg.20211399
dc.identifier.isbn978-3-03868-162-5
dc.identifier.pages93-98
dc.identifier.urihttps://doi.org/10.2312/pg.20211399
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/pg20211399
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.titleGANST: Gradient-aware Arbitrary Neural Style Transferen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
093-098.pdf
Size:
5.69 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2021 Short Papers, Posters, and Work-in-Progress Papers