CubeGAN: Omnidirectional Image Synthesis Using Generative Adversarial Networks

Simple item page
dc.contributor.authorMay, Christopheren_US
dc.contributor.authorAliaga, Danielen_US
dc.contributor.editorMyszkowski, Karolen_US
dc.contributor.editorNiessner, Matthiasen_US
dc.date.accessioned2023-05-03T06:10:08Z
dc.date.available2023-05-03T06:10:08Z
dc.date.issued2023
dc.description.abstractWe propose a framework to create projectively-correct and seam-free cube-map images using generative adversarial learning. Deep generation of cube-maps that contain the correct projection of the environment onto its faces is not straightforward as has been recognized in prior work. Our approach extends an existing framework, StyleGAN3, to produce cube-maps instead of planar images. In addition to reshaping the output, we include a cube-specific volumetric initialization component, a projective resampling component, and a modification of augmentation operations to the spherical domain. Our results demonstrate the network's generation capabilities trained on imagery from various 3D environments. Additionally, we show the power and quality of our GAN design in an inversion task, combined with navigation capabilities, to perform novel view synthesis.en_US
dc.description.number2
dc.description.sectionheadersBRDFs and Environment Maps
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14755
dc.identifier.issn1467-8659
dc.identifier.pages213-224
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14755
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14755
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Computer graphics; Rendering; Neural networks
dc.subjectComputing methodologies
dc.subjectComputer graphics
dc.subjectRendering
dc.subjectNeural networks
dc.titleCubeGAN: Omnidirectional Image Synthesis Using Generative Adversarial Networksen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
v42i2pp213-224_cgf14755.pdf
Size:
20.87 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1134_mm.mp4
Size:
28.18 MB
Format:
Unknown data format
Download
Collections
42-Issue 2