• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Pixel-Wise Confidences for Stereo Disparities Using Recurrent Neural Networks
 
  • Details
  • Full
Options
2019
Conference Paper
Titel

Pixel-Wise Confidences for Stereo Disparities Using Recurrent Neural Networks

Abstract
One of the inherent problems with stereo disparity estimation algorithms is the lack of reliability information for the computed disparities. As a consequence, errors from the initial disparity maps are propagated to the following processing steps such as view rendering. Nowadays, confidence measures belong to the most popular techniques because of their capability to detect disparity outliers. Recently, convolutional neural network based confidence measures achieved best results by directly processing initial disparity maps. In contrast to existing convolutional neural network based methods, we propose a novel recurrent neural network architecture to compute confidences for different stereo matching algorithms. To maintain a low complexity the confidence for a given pixel is purely computed from its associated matching costs without considering any additional neighbouring pixels. As compared to the state-of-the-art confidence prediction methods leveraging convolutional neural networks, the proposed network is simpler and smaller in terms of size (reduction of the number of trainable parameters by almost 3-4 orders of magnitude). Moreover, the experimental results on three well-known datasets as well as with two popular stereo algorithms clearly highlight that the proposed approach outperforms state-of-the-art confidence estimation techniques.
Author(s)
Gul, Muhammad Shahzeb Khan
Fraunhofer-Institut für Integrierte Schaltungen IIS
Bätz, Michel
Fraunhofer-Institut für Integrierte Schaltungen IIS
Keinert, Joachim
Fraunhofer-Institut für Integrierte Schaltungen IIS
Hauptwerk
30th British Machine Vision Conference, BMVC 2019. Detailed Programme. Online resource
Project(s)
RealVision
Funder
European Commission EC
Konferenz
British Machine Vision Conference (BMVC) 2019
DOI
10.24406/iis-n-581312
File(s)
N-581312.pdf (880.1 KB)
Language
English
google-scholar
Fraunhofer-Institut für Integrierte Schaltungen IIS
Tags
  • Lichtfeld

  • Image Based Rendering...

  • computational imaging...

  • Bildverarbeitung

  • Algorithmen

  • 3D Bildverarbeitung

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022