This is the supplementary materials for the paper
 
    "Adaptive Manifolds for Real-Time High-Dimensional Filtering"
           Eduardo S. L. Gastal  and  Manuel M. Oliveira

For up-to-date information refer to our Project Website:

           http://inf.ufrgs.br/~eslgastal/AdaptiveManifolds


In the "Examples_and_Comparisons" folder you will find an "index.html" file
which can be opened in any web browser. This file contains various examples
illustrating some of the possible applications of our adaptive-manifold
high-dimensional filter, as well as PSNR data and comparison images.

Important: These materials are best viewed in a web browser that is *not*
Internet Explorer (IE), since it cannot resize the images properly.
Furthermore, in IE you might need to allow ActiveX content to display the
images.

Performance numbers can be found in the paper. A GPU performance graph and some
extra mathematical derivations can be found in the supplementary PDF.

Additionally, we have included in this zip file a video which helps explain the
intuition behind our technique. It also shows the application of our method to
filter a high-resolution 1920x1080 video at 0.007 sec per frame.


=== Copyright notice

The original input 1080p videos shown between 5:24 and 5:51 in the
"Adaptive_Manifolds.wmv" video have the following license:

These video sequences are owned by NTIA/ITS, an agency of the U.S. Federal
Government.  They were created under Project Number 3141012-300, Video Quality
Research, in 2008.  These video sequences may be used for research purposes,
only.  You can use, copy, modify and redistribute them upon your acceptance of
these terms and conditions and upon your express agreement to provide
appropriate acknowledgments of NTIA/ITS's ownership of the video sequences by
keeping this text present with any copied or derived works.

Video Standard: 1080p 30fps
Camera specs:   Panasonic AJ-HDX-900, saved to DVCPro tape.
Video standard: Native
Editing:        19 second clips, intended to remove first 2-sec and final 2-sec.
Scenes:
      Aspen
      RedKayak