Back to articles
Volume: 26 | Article ID: art00047
Color-based Data Augmentation for Reflectance Estimation
  DOI :  10.2352/ISSN.2169-2629.2018.26.284  Published OnlineNovember 2018

Deep convolutional architectures have shown to be successful frameworks to solve generic computer vision problems. The estimation of intrinsic reflectance from single image is not a solved problem yet. Encoder-Decoder architectures are a perfect approach for pixel-wise reflectance estimation, although it usually suffers from the lack of large datasets. Lack of data can be partially solved with data augmentation, however usual techniques focus on geometric changes which does not help for reflectance estimation. In this paper we propose a color-based data augmentation technique that extends the training data by increasing the variability of chromaticity. Rotation on the red-green blue-yellow plane of an opponent space enable to increase the training set in a coherent and sound way that improves network generalization capability for reflectance estimation. We perform some experiments on the Sintel dataset showing that our color-based augmentation increase performance and overcomes one of the state-of-the-art methods.

Subject Areas :
Views 19
Downloads 6
 articleview.views 19
 articleview.downloads 6
  Cite this article 

H. Sial, S. Sancho-Asensio, R. Baldrich, R. Benavente, M. Vanrell, "Color-based Data Augmentation for Reflectance Estimationin Proc. IS&T 26th Color and Imaging Conf.,  2018,  pp 284 - 289,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2018
Color and Imaging Conference
color imaging conf
Society for Imaging Science and Technology