A Deep Residual Network for Geometric Decontouring

dc.contributor.authorJi, Zhongpingen_US
dc.contributor.authorZhou, Chengqinen_US
dc.contributor.authorZhang, Qiankanen_US
dc.contributor.authorZhang, Yu-Weien_US
dc.contributor.authorWang, Wenpingen_US
dc.contributor.editorEisemann, Elmar and Jacobson, Alec and Zhang, Fang-Lueen_US
dc.date.accessioned2020-10-29T18:49:53Z
dc.date.available2020-10-29T18:49:53Z
dc.date.issued2020
dc.description.abstractGrayscale images are intensively used to construct or represent geometric details in field of computer graphics. In practice, displacement mapping technique often allows an 8-bit grayscale image input to manipulate the position of vertices. Human eyes are insensitive to the change of intensity between consecutive gray levels, so a grayscale image only provides 256 levels of luminances. However, when the luminances are converted into geometric elements, certain artifacts such as false contours become obvious. In this paper, we formulate the geometric decontouring as a constrained optimization problem from a geometric perspective. Instead of directly solving this optimization problem, we propose a data-driven method to learn a residual mapping function. We design a Geometric DeContouring Network (GDCNet) to eliminate the false contours effectively. To this end, we adopt a ResNet-based network structure and a normal-based loss function. Extensive experimental results demonstrate that accurate reconstructions can be achieved effectively. Our method can be used as a relief compressed representation and enhance the traditional displacement mapping technique to augment 3D models with high-quality geometric details using grayscale images efficiently.en_US
dc.description.number7
dc.description.sectionheadersGeometry and Modeling
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14124
dc.identifier.issn1467-8659
dc.identifier.pages27-41
dc.identifier.urihttps://doi.org/10.1111/cgf.14124
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14124
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectHeight map
dc.subjectFalse contour
dc.subjectResidual network
dc.subjectGeometric decontouring
dc.subjectConstrained optimization
dc.titleA Deep Residual Network for Geometric Decontouringen_US
Files
Collections