English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination

Georgoulis, S., Rematas, K., Ritschel, T., Fritz, M., Van Gool, L., & Tuytelaars, T. (2016). DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination. Retrieved from http://arxiv.org/abs/1603.08240.

Item is

Basic

show hide
Genre: Paper
Latex : {DeLight-Net}: {D}ecomposing Reflectance Maps into Specular Materials and Natural Illumination

Files

show Files
hide Files
:
arXiv:1603.08240.pdf (Preprint), 5MB
Name:
arXiv:1603.08240.pdf
Description:
File downloaded from arXiv at 2016-07-14 16:30
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, Konstantinos1, Author           
Ritschel, Tobias1, Author           
Fritz, Mario2, Author           
Van Gool, Luc1, Author
Tuytelaars, Tinne1, Author
Affiliations:
1External Organizations, ou_persistent22              
2Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Abstract: In this paper we are extracting surface reflectance and natural environmental illumination from a reflectance map, i.e. from a single 2D image of a sphere of one material under one illumination. This is a notoriously difficult problem, yet key to various re-rendering applications. With the recent advances in estimating reflectance maps from 2D images their further decomposition has become increasingly relevant. To this end, we propose a Convolutional Neural Network (CNN) architecture to reconstruct both material parameters (i.e. Phong) as well as illumination (i.e. high-resolution spherical illumination maps), that is solely trained on synthetic data. We demonstrate that decomposition of synthetic as well as real photographs of reflectance maps, both in High Dynamic Range (HDR), and, for the first time, on Low Dynamic Range (LDR) as well. Results are compared to previous approaches quantitatively as well as qualitatively in terms of re-renderings where illumination, material, view or shape are changed.

Details

show
hide
Language(s): eng - English
 Dates: 2016-03-272016
 Publication Status: Published online
 Pages: 16 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1603.08240
URI: http://arxiv.org/abs/1603.08240
BibTex Citekey: Georgoulis_arXiv2016
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show