Abstract Painting Synthesis via Decremental optimization

Simple item page
dc.contributor.authorYan, Mingen_US
dc.contributor.authorPu, Yuanyuanen_US
dc.contributor.authorZhao, Pengzhengen_US
dc.contributor.authorXu, Danen_US
dc.contributor.authorWu, Haoen_US
dc.contributor.authorYang, Qiuxiaen_US
dc.contributor.authorWang, Ruxinen_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:41:27Z
dc.date.available2022-10-04T06:41:27Z
dc.date.issued2022
dc.description.abstractExisting stroke-based painting synthesis methods usually fail to achieve good results with limited strokes because these methods use semantically irrelevant metrics to calculate the similarity between the painting and photo domains. Hence, it is hard to see meaningful semantical information from the painting. This paper proposes a painting synthesis method that uses a CLIP (Contrastive-Language-Image-Pretraining) model to build a semantically-aware metric so that the cross-domain semantic similarity is explicitly involved. To ensure the convergence of the objective function, we design a new strategy called decremental optimization. Specifically, we define painting as a set of strokes and use a neural renderer to obtain a rasterized painting by optimizing the stroke control parameters through a CLIP-based loss. The optimization process is initialized with an excessive number of brush strokes, and the number of strokes is then gradually reduced to generate paintings of varying levels of abstraction. Experiments show that our method can obtain vivid paintings, and the results are better than the comparison stroke-based painting synthesis methods when the number of strokes is limited.en_US
dc.description.number7
dc.description.sectionheadersImage Synthesis
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14688
dc.identifier.issn1467-8659
dc.identifier.pages419-430
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14688
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14688
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computer Graphics → Non-photorealistic rendering; Stroke based rendering
dc.subjectComputer Graphics → Non
dc.subjectphotorealistic rendering
dc.subjectStroke based rendering
dc.titleAbstract Painting Synthesis via Decremental optimizationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v41i7pp419-430.pdf
Size:
7.54 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 7