The Library
A machine learning driven sky model
Tools
Tools
Tools
Satilmis, Pinar, Bashford-Rogers, Thomas, Chalmers, Alan and Debattista, Kurt (2017) A machine learning driven sky model. IEEE Computer Graphics and Applications, 37 (1). pp. 80-91. doi:10.1109/MCG.2016.67
|
PDF
WRAP_mldsm_pinar_s.pdf - Accepted Version - Requires a PDF viewer. Download (11Mb) | Preview |
Official URL: http://dx.doi.org/10.1109/MCG.2016.67
Abstract
Sky illumination is important for generating realistic renderings of virtual environments in a number of applications ranging from entertainment to archaeology. Current solutions use complex analytical models which can be costly to compute interactively; or require the capture of sky environment maps which constitute a laborious and impractical task in order to obtain smooth animations. In this work, we present an alternative model for sky illumination based on machine learning. This approach compactly represents sky illumination from both existing analytic sky models and from captured environment maps. For analytic models, our approach leads to a low, constant runtime cost for evaluating lighting. When applied to environment maps, our approach approximates the captured lighting at a significantly reduced memory cost, and enables smooth transitions of sky lighting to be created from a small set of environment maps captured at discrete times of day. This makes capture and rendering of real world sky illumination a practical proposition. Our method encodes the non-linear mapping of sun and view direction to radiance values using a single layer Artificial Neural Network. The network is trained using a sparse set of samples which capture the properties of the lighting at various sun positions. Results demonstrate accuracy close to the ground truth for both analytical and capture based methods. Our approach has a low runtime overhead meaning that it can be used as a generic approach for both offline and real-time applications.
| Item Type: | Journal Article | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software | ||||||||
| Divisions: | Faculty of Science > WMG (Formerly the Warwick Manufacturing Group) | ||||||||
| Library of Congress Subject Headings (LCSH): | Computer graphics, Machine learning, Neural circuitry | ||||||||
| Journal or Publication Title: | IEEE Computer Graphics and Applications | ||||||||
| Publisher: | Institute of Electrical and Electronics Engineers | ||||||||
| ISSN: | 0272-1716 | ||||||||
| Official Date: | January 2017 | ||||||||
| Dates: |
|
||||||||
| Date of first compliant deposit: | 28 June 2016 | ||||||||
| Volume: | 37 | ||||||||
| Number: | 1 | ||||||||
| Number of Pages: | 9 | ||||||||
| Page Range: | pp. 80-91 | ||||||||
| DOI: | 10.1109/MCG.2016.67 | ||||||||
| Status: | Peer Reviewed | ||||||||
| Publication Status: | Published | ||||||||
| Access rights to Published version: | Restricted or Subscription Access |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
Downloads
Downloads per month over past year
