Efficient Image-Warping Framework for Content-Adaptive Superpixels Generation

Research output: Contribution to journalArticleScientificpeer-review


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 efciently 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.

Original languageEnglish
Pages (from-to)1948-1952
Number of pages5
JournalIEEE Signal Processing Letters
Publication statusPublished - 2021
Publication typeA1 Journal article-refereed


  • Content-adaptive superpixels
  • efficiency
  • GPU
  • Image edge detection
  • Image resolution
  • Image segmentation
  • Optimization
  • Signal processing algorithms
  • Time complexity
  • Transforms

Publication forum classification

  • Publication forum level 2

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics


Dive into the research topics of 'Efficient Image-Warping Framework for Content-Adaptive Superpixels Generation'. Together they form a unique fingerprint.

Cite this