Show simple item record

dc.contributor.authorWang, Jieen_US
dc.contributor.authorWang, Yongzhenen_US
dc.contributor.authorFeng, Yidanen_US
dc.contributor.authorGong, Linaen_US
dc.contributor.authorYan, Xuefengen_US
dc.contributor.authorXie, Haoranen_US
dc.contributor.authorWang, Fu Leeen_US
dc.contributor.authorWei, Mingqiangen_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:41:16Z
dc.date.available2022-10-04T06:41:16Z
dc.date.issued2022
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14681
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14681
dc.description.abstractImage smoothing is a fundamental low-level vision task that aims to preserve salient structures of an image while removing insignificant details. Deep learning has been explored in image smoothing to deal with the complex entanglement of semantic structures and trivial details. However, current methods neglect two important facts in smoothing: 1) naive pixel-level regression supervised by the limited number of high-quality smoothing ground-truth could lead to domain shift and cause generalization problems towards real-world images; 2) texture appearance is closely related to object semantics, so that image smoothing requires awareness of semantic difference to apply adaptive smoothing strengths. To address these issues, we propose a novel Contrastive Semantic-Guided Image Smoothing Network (CSGIS-Net) that combines both contrastive prior and semantic prior to facilitate robust image smoothing. The supervision signal is augmented by leveraging undesired smoothing effects as negative teachers, and by incorporating segmentation tasks to encourage semantic distinctiveness. To realize the proposed network, we also enrich the original VOC dataset with texture enhancement and smoothing labels, namely VOC-smooth, which first bridges image smoothing and semantic segmentation. Extensive experiments demonstrate that the proposed CSGIS-Net outperforms state-of-the-art algorithms by a large margin. Code and dataset are available at https://github.com/wangjie6866/CSGIS-Net.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies --> Image processing
dc.subjectComputing methodologies
dc.subjectImage processing
dc.titleContrastive Semantic-Guided Image Smoothing Networken_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersImage Enhancement
dc.description.volume41
dc.description.number7
dc.identifier.doi10.1111/cgf.14681
dc.identifier.pages335-346
dc.identifier.pages12 pages


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • 41-Issue 7
    Pacific Graphics 2022 - Symposium Proceedings

Show simple item record