SkyGAN: Realistic Cloud Imagery for Image-based Lighting
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10474505" target="_blank" >RIV/00216208:11320/23:10474505 - isvavai.cz</a>
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=i~Jo4Y7yRk" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=i~Jo4Y7yRk</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1111/cgf.14990" target="_blank" >10.1111/cgf.14990</a>
Alternative languages
Result language
angličtina
Original language name
SkyGAN: Realistic Cloud Imagery for Image-based Lighting
Original language description
Achieving 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. Our source code and a dataset of 39 000 HDR sky images are publicly available at at https://github.com/CGGMFF/SkyGAN.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF19_073%2F0016935" target="_blank" >EF19_073/0016935: Grant schemes at Charles University</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Computer Graphics Forum
ISSN
0167-7055
e-ISSN
1467-8659
Volume of the periodical
Neuveden
Issue of the periodical within the volume
2023-11-17
Country of publishing house
GB - UNITED KINGDOM
Number of pages
12
Pages from-to
—
UT code for WoS article
001106236600001
EID of the result in the Scopus database
2-s2.0-85176594152