English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Natural Illumination from Multiple Materials Using Deep Learning

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.

Item is

Files

show Files
hide Files
:
arXiv:1611.09325.pdf (Preprint), 8MB
Name:
arXiv:1611.09325.pdf
Description:
File downloaded from arXiv at 2016-12-19 15:11
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Georgoulis, Stamatios1, Author
Rematas, Konstantinos2, Author           
Ritschel, Tobias3, Author           
Fritz, Mario2, Author           
Tuytelaars, Tinne1, Author
Van Gool, Luc1, Author
Affiliations:
1External Organizations, ou_persistent22              
2Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
3Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 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.

Details

show
hide
Language(s): eng - English
 Dates: 2016-11-282016
 Publication Status: Published online
 Pages: 10 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1611.09325
URI: http://arxiv.org/abs/1611.09325
BibTex Citekey: Fritzarxiv16
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show