Skip to main content

Research Repository

Advanced Search

Deep synthesis of cloud lighting

Satilmis, Pinar; Marnerides, Demetris; Debattista, Kurt; Bashford-Rogers, Thomas

Deep synthesis of cloud lighting Thumbnail


Pinar Satilmis

Demetris Marnerides

Kurt Debattista


Current appearance models for the sky are able to represent clear sky illumination to a high degree of accuracy. However, these models all lack a common feature of real-skies: clouds. These are an essential component for many applications which rely on realistic skies, such as image editing and synthesis. While clouds can be added to existing sky models through rendering, this is hard to achieve due to the difficulties of representing clouds and the complexities of volumetric light transport. In this work, an alternative approach to this problem is proposed whereby clouds are synthesized using a learned data-driven representation. This leverages a captured collection of High Dynamic Range cloudy sky imagery, and combines this dataset with clear sky models to produce plausible cloud appearance from a coarse representation of cloud positions. This representation is artist controllable, allowing for novel cloudscapes to be rapidly synthesized, and used for lighting virtual environments.


Satilmis, P., Marnerides, D., Debattista, K., & Bashford-Rogers, T. (2022). Deep synthesis of cloud lighting. IEEE Computer Graphics and Applications, 42(5; 01 Sept.-Oct. 2022), 8 - 18.

Journal Article Type Article
Acceptance Date May 2, 2022
Online Publication Date May 5, 2022
Publication Date Sep 1, 2022
Deposit Date Jun 16, 2022
Publicly Available Date Jun 17, 2022
Journal IEEE Computer Graphics and Applications
Print ISSN 0272-1716
Electronic ISSN 1558-1756
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
Volume 42
Issue 5; 01 Sept.-Oct. 2022
Pages 8 - 18
Keywords Computer Graphics and Computer-Aided Design; Software; Cloud computing;Clouds; Lighting; Atmospheric modeling; Computational modeling; Rendering (computer graphics); Neural networks
Public URL


Deep synthesis of cloud lighting (21.8 Mb)


Publisher Licence URL

Copyright Statement
This is the author’s accepted manuscript. The final published version is available here:
(c) 2021 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See for more information

You might also like

Downloadable Citations