SkyGAN: Towards Realistic Cloud Imagery for Image Based Lighting

Simple item page
dc.contributor.authorMirbauer, Martinen_US
dc.contributor.authorRittig, Tobiasen_US
dc.contributor.authorIser, Tomášen_US
dc.contributor.authorKrivánek, Jaroslaven_US
dc.contributor.authorŠikudová, Elenaen_US
dc.contributor.editorGhosh, Abhijeeten_US
dc.contributor.editorWei, Li-Yien_US
dc.date.accessioned2022-07-01T15:37:38Z
dc.date.available2022-07-01T15:37:38Z
dc.date.issued2022
dc.description.abstractAchieving photorealism when rendering virtual scenes in movies or architecture visualizations often depends on providing a realistic illumination and background. Typically, spherical environment maps serve both as a natural light source from the Sun and the sky, and as a background with clouds and a horizon. In practice, the input is either a static high-resolution HDR photograph manually captured on location in real conditions, or an analytical clear sky model that is dynamic, but cannot model clouds. Our approach bridges these two limited paradigms: a user can control the sun position and cloud coverage ratio, and generate a realistically looking environment map for these conditions. It is a hybrid data-driven analytical model based on a modified state-of-the-art GAN architecture, which is trained on matching pairs of physically-accurate clear sky radiance and HDR fisheye photographs of clouds. We demonstrate our results on renders of outdoor scenes under varying time, date, and cloud covers.en_US
dc.description.sectionheadersLighting
dc.description.seriesinformationEurographics Symposium on Rendering
dc.identifier.doi10.2312/sr.20221151
dc.identifier.isbn978-3-03868-187-8
dc.identifier.issn1727-3463
dc.identifier.pages13-22
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/sr.20221151
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/sr20221151
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 --> Rendering; Supervised learning; Applied computing --> Earth and atmospheric sciences
dc.subjectComputing methodologies
dc.subjectRendering
dc.subjectSupervised learning
dc.subjectApplied computing
dc.subjectEarth and atmospheric sciences
dc.titleSkyGAN: Towards Realistic Cloud Imagery for Image Based Lightingen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
013-022.pdf
Size:
3.65 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1043_mm.mp4
Size:
89.08 MB
Format:
Unknown data format
Download
Thumbnail Image
Name:
paper1043_mm.pdf
Size:
10.71 MB
Format:
Adobe Portable Document Format
Download
Collections
Rendering 2022 - Symposium Track