Efficient Texture Parameterization Driven by Perceptual-Loss-on-Screen

Simple item page
dc.contributor.authorSun, Haoranen_US
dc.contributor.authorWang, Shiyien_US
dc.contributor.authorWu, Wenhaien_US
dc.contributor.authorJin, Yaoen_US
dc.contributor.authorBao, Hujunen_US
dc.contributor.authorHuang, Jinen_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:41:36Z
dc.date.available2022-10-04T06:41:36Z
dc.date.issued2022
dc.description.abstractTexture mapping is a ubiquitous technique to enrich the visual effect of a mesh, which represents the desired signal (e.g. diffuse color) on the mesh to a texture image discretized by pixels through a bijective parameterization. To achieve high visual quality, large number of pixels are generally required, which brings big burden in storage, memory and transmission. We propose to use a perceptual model and a rendering procedure to measure the loss coming from the discretization, then optimize a parameterization to improve the efficiency, i.e. using fewer pixels under a comparable perceptual loss. The general perceptual model and rendering procedure can be very complicated, and non-isotropic property rooted in the square shape of pixels make the problem more difficult to solve. We adopt a two-stage strategy and use the Bayesian optimization in the triangle-wise stage. With our carefully designed weighting scheme, the mesh-wise optimization can take the triangle-wise perceptual loss into consideration under a global conforming requirement. Comparing with many parameterizations manually designed, driven by interpolation error, or driven by isotropic energy, ours can use significantly fewer pixels with comparable perception loss or vise vesa.en_US
dc.description.number7
dc.description.sectionheadersStylization and Texture
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14696
dc.identifier.issn1467-8659
dc.identifier.pages507-518
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14696
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14696
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectKeywords: Geometric Modeling, Surface Parameterization, Texture Mapping, Perceptual Loss CCS Concepts: Computing methodologies → Shape modeling
dc.subjectGeometric Modeling
dc.subjectSurface Parameterization
dc.subjectTexture Mapping
dc.subjectPerceptual Loss CCS Concepts
dc.subjectComputing methodologies → Shape modeling
dc.titleEfficient Texture Parameterization Driven by Perceptual-Loss-on-Screenen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v41i7pp507-518.pdf
Size:
11.32 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 7