JPEG Line-drawing Restoration With Masks

Simple item page
dc.contributor.authorZhu, Yanen_US
dc.contributor.authorYamaguchi, Yasushien_US
dc.contributor.editorBanterle, Francescoen_US
dc.contributor.editorCaggianese, Giuseppeen_US
dc.contributor.editorCapece, Nicolaen_US
dc.contributor.editorErra, Ugoen_US
dc.contributor.editorLupinetti, Katiaen_US
dc.contributor.editorManfredi, Gildaen_US
dc.date.accessioned2023-11-12T15:37:39Z
dc.date.available2023-11-12T15:37:39Z
dc.date.issued2023
dc.description.abstractLearning-based JPEG restoration methods usually lack consideration on the visual content of images. Even though these methods achieve satisfying results on photos, the direct application of them on line drawings, which consist of lines and white background, is not suitable. The large area of background in digital line drawings does not contain intensity information and should be constantly white (the maximum brightness). Existing JPEG restoration networks consistently fail to output constant white pixels for the background area. What's worse, training on the background can negatively impact the learning efficiency for areas where texture exists. To tackle these problems, we propose a line-drawing restoration framework that can be applied to existing state-of-the-art restoration networks. Our framework takes existing restoration networks as backbones and processes an input rasterized JPEG line drawing in two steps. First, a proposed mask-predicting network predicts a binary mask which indicates the location of lines and background in the potential undeteriorated line drawing. Then, the mask is concatenated with the input JPEG line drawing and fed into the backbone restoration network, where the conventional L1 loss is replaced by a masked Mean Square Error (MSE) loss. Besides learning-based mask generation, we also evaluate other direct mask generation methods. Experiments show that our framework with learnt binary masks achieves both better visual quality and better performance on quantitative metrics than the state-of-the-art methods in the task of JPEG line-drawing restoration.en_US
dc.description.sectionheadersOptimizations for Computer Graphics
dc.description.seriesinformationSmart Tools and Applications in Graphics - Eurographics Italian Chapter Conference
dc.identifier.doi10.2312/stag.20231299
dc.identifier.isbn978-3-03868-235-6
dc.identifier.issn2617-4855
dc.identifier.pages103-111
dc.identifier.pages9 pages
dc.identifier.urihttps://doi.org/10.2312/stag.20231299
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/stag20231299
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Reconstruction; Image processing; Applied computing -> Media arts
dc.subjectComputing methodologies
dc.subjectReconstruction
dc.subjectImage processing
dc.subjectApplied computing
dc.subjectMedia arts
dc.titleJPEG Line-drawing Restoration With Masksen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
103-111.pdf
Size:
8.64 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Italian Chapter Conference 2023 - Smart Tools and Apps in Graphics