Thursday, September 17, 2009

A bad news

Their results for comparison


http://www.iro.umontreal.ca/~ostrom/publications/pdf/SIGGRAPH-ASIA09_saed.pdf
This paper is published in this year SIGGRAPH-ASIA. They did the error diffusion very very fast and have the structure well maintained.

3 comments:

  1. Thanks for finding this -- very useful.

    In your opinion, is there anything to salvage from the method? It does not seem to be as fast as SAED and it is not obvious to me that the results will be any better.

    ReplyDelete
  2. I forgot to mention if we do not do the ordering, our method can be done 5 seconds for Lena(512 by 512).

    ReplyDelete
  3. Actually, I kind like the non-ordered method. The structure measurement and the contrast measurement are better than 'structure-aware' paper. Even the tone is better than their results, but usually worse than those results from the traditional error diffusion.

    ReplyDelete