Affordable Access

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

Authors
  • Georgoulis, Stamatios
  • Rematas, Konstantinos
  • Ritschel, Tobias
  • Fritz, Mario
  • Van Gool, Luc
  • Tuytelaars, Tinne
Type
Preprint
Publication Date
Mar 27, 2016
Submission Date
Mar 27, 2016
Identifiers
arXiv ID: 1603.08240
Source
arXiv
License
Yellow
External links

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.

Report this publication

Statistics

Seen <100 times