"Efficient Image-Warping Framework for Content-Adaptive Superpixels Generation" accepted for publication

The article "Efficient Image-Warping Framework for Content-Adaptive Superpixels Generation" by Aleksandra Chuchvara and Atanas Gotchev has been accepted for publication in a future issue of IEEE Signal Processing Letters and is available under the "Early Access" area on IEEE Xplore.

Abstract:

We address the problem of efficient content-adaptive superpixel segmentation. Instead of adapting the size and/or amount of superpixels to the image content, we propose a warping transform that makes the image content more suitable to be segmented into regular superpixels. Regular superpixels in the warped image induce content-adaptive superpixels in the original image with improved segmentation accuracy. To efficiently compute the warping transform, we develop an iterative coarse-to-fine optimization procedure and employ a parallelization strategy allowing for a speedy GPU-based implementation. The proposed solution works as a simple add-on framework over an underlying segmentation algorithm and requires no additional parameters. Evaluations on the Berkeley segmentation dataset verify that our approach provides competitive quality results compared to the state-of-the-art methods and achieves a better time-accuracy trade-off. We further demonstrate the effectiveness of our method with an application to disparity estimation.

Contact person

Aleksandra Chuchvara 3D Media Group Tampere University

Aleksandra Chuchvara

  • Doctoral Researcher
  • Hervanta Campus, TE308
  • Faculty of Information Technology and Communication Sciences, Computing Sciences
  • aleksandra.chuchvara@tuni.fi
More information
Professor Atanas Gotchev 3D Media Group

Atanas Gotchev

  • Professor, Signal Processing
  • Hervanta Campus, TE314
  • Faculty of Information Technology and Communication Sciences, Computing Sciences
  • +358408490733
  • atanas.gotchev@tuni.fi
More information