Semantic Segmentation for Line Drawing Vectorization Using Neural Networks

dc.contributor.authorKim, Byungsooen_US
dc.contributor.authorWang, Oliveren_US
dc.contributor.authorÖztireli, A. Cengizen_US
dc.contributor.authorGross, Markusen_US
dc.contributor.editorGutierrez, Diego and Sheffer, Allaen_US
dc.date.accessioned2018-04-14T18:24:51Z
dc.date.available2018-04-14T18:24:51Z
dc.date.issued2018
dc.description.abstractIn this work, we present a method to vectorize raster images of line art. Inverting the rasterization procedure is inherently ill-conditioned, as there exist many possible vector images that could yield the same raster image. However, not all of these vector images are equally useful to the user, especially if performing further edits is desired. We therefore define the problem of computing an instance segmentation of the most likely set of paths that could have created the raster image. Once the segmentation is computed, we use existing vectorization approaches to vectorize each path, and then combine all paths into the final output vector image. To determine which set of paths is most likely, we train a pair of neural networks to provide semantic clues that help resolve ambiguities at intersection and overlap regions. These predictions are made considering the full context of the image, and are then globally combined by solving a Markov Random Field (MRF). We demonstrate the flexibility of our method by generating results on character datasets, a synthetic random line dataset, and a dataset composed of human drawn sketches. For all cases, our system accurately recovers paths that adhere to the semantics of the drawings.en_US
dc.description.number2
dc.description.sectionheadersSegmentation and Noise
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume37
dc.identifier.doi10.1111/cgf.13365
dc.identifier.issn1467-8659
dc.identifier.pages329-338
dc.identifier.urihttps://doi.org/10.1111/cgf.13365
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13365
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectImage manipulation
dc.subjectComputational photography
dc.titleSemantic Segmentation for Line Drawing Vectorization Using Neural Networksen_US
Files
Collections