de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Natural Illumination from Multiple Materials Using Deep Learning

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons127690

Rematas,  Konstantinos
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45298

Ritschel,  Tobias
Computer Graphics, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons44451

Fritz,  Mario
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1611.09325.pdf
(Preprint), 8MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Georgoulis, S., Rematas, K., Ritschel, T., Fritz, M., Tuytelaars, T., & Van Gool, L. (2016). Natural Illumination from Multiple Materials Using Deep Learning. Retrieved from http://arxiv.org/abs/1611.09325.


Cite as: http://hdl.handle.net/11858/00-001M-0000-002C-270F-0
Abstract
Recovering natural illumination from a single Low-Dynamic Range (LDR) image is a challenging task. To remedy this situation we exploit two properties often found in everyday images. First, images rarely show a single material, but rather multiple ones that all reflect the same illumination. However, the appearance of each material is observed only for some surface orientations, not all. Second, parts of the illumination are often directly observed in the background, without being affected by reflection. Typically, this directly observed part of the illumination is even smaller. We propose a deep Convolutional Neural Network (CNN) that combines prior knowledge about the statistics of illumination and reflectance with an input that makes explicit use of these two observations. Our approach maps multiple partial LDR material observations represented as reflectance maps and a background image to a spherical High-Dynamic Range (HDR) illumination map. For training and testing we propose a new data set comprising of synthetic and real images with multiple materials observed under the same illumination. Qualitative and quantitative evidence shows how both multi-material and using a background are essential to improve illumination estimations.