Alpha Matting Evaluation Website
www.alphamatting.com

Christoph RhemannCarsten RotherJue WangMargrit GelautzPushmeet Kohli • Pamela Rott

This website accompanies our CVPR 2009 paper [1].

If you report results of this benchmark, we request that you cite our paper [1].

References:
[1] Christoph Rhemann, Carsten Rother, Jue Wang, Margrit Gelautz, Pushmeet Kohli, Pamela Rott. A Perceptually Motivated Online Benchmark for Image Matting.
Conference on Computer Vision and Pattern Recognition (CVPR), June 2009.

News:
  • 24. Oct. 2017: Source code for "Three-layer Graph Framework" available-see the code page.
  • 02. Oct. 2014: Source code for "Comprehensive Weighted Color and Texture" available-see the code page.
  • 02. Oct. 2014: Source code for "Comprehensive sampling method" available-see the code page.
  • 27. Nov. 2013: Website for ICCV 2013 tutorial on Image and Video Matting is now available-see the tutorial page.
  • 10. Sept. 2012: Code for "KNN Matting" available-see the code page.
  • 20. May 2011: Code for "Learning Based Matting" available-see the code page.
  • 10. June 2010: Added 4 more methods to the evaluation - the evaluation now comprises 15 methods in total.
  • 20. Oct. 2009: Added 4 more methods to the evaluation.
  • 21. Sept. 2009: We now also provide the ground foreground colors for the images in the training dataset for those who need them.
  • Due to computational reasons we use a connectivity measure for evaluation on this webpage that slightly differs from the measure that was described in the original CVPR'09 paper. Please refer to our technical report for further details:
    [2] Christoph Rhemann, Carsten Rother, Jue Wang, Margrit Gelautz, Pushmeet Kohli, Pamela Rott. A Perceptually Motivated Online Benchmark for Image Matting.
    Technical Report TR-188-2-2009-03, May 2009.

  • Submission page is now open.

 

This work was supported in part by Microsoft Research Cambridge through its PhD Scholarship Programme and a travel sponsorship.
This website is funded by the Vienna Science and Technology Fund (WWTF) through project ICT08-019