QuickTopic free message boards logo
Skip to Messages

TOPIC:

On Perpendicular Texture: Why do we see more flowers in the distance?

8
MasooriPerson was signed in when posted
10-03-2016
05:13 AM ET (US)
Amazing post, continue writing like this..
acmecoolant
  Messages 7-6 deleted by author between 07-23-2006 02:07 AM and 07-21-2006 09:00 AM
5
Rasit Topaloglu
11-16-2004
03:36 AM ET (US)
Why would the Poisson distribution be the best model for the location of elements?
4
Deleted by author 11-16-2004 01:36 AM
3
Robin Hewitt
11-15-2004
06:38 PM ET (US)
I was surprised that what they call perpendicular texture had been little studied. This paper is from 97. I wonder if that's still the case?
2
Steve Scher
11-15-2004
05:50 PM ET (US)
The most important part of this, I think, is the simple idea that, in the situation assumed in the paper (a field of similar texture objects on a simple surface), for any region of the image:

Occlusion will cause the viewing geometry to dictate how much of the field of view is filled by the top of the texture-object, and how much is filled by the bottom.

This means that you can measure how much of each part of the texture-object you see (by color or some other feature) and determine what the viewing geometry/surface geometry is for that region of the image.

This paper interests me mostly in the possibility of using raw data to learn the features that indicate the top vs bottom of the texture object (rather than starting out knowing that the simple feature of color alone is a enough, and that yellow is the top, green the bottom.

You can skip section 5 if you'd like, it makes the generalization from planar surfaces to curved surfaces.
1
Steve Scher
11-15-2004
02:45 PM ET (US)
If the link to the PDF doesn't work, there's a postscript copy available at:

http://www.cs.berkeley.edu/~leungt/Research/CVPR97.ps.gz

I can also email out a PDF copy.

Print | RSS Views: 1939 (Unique: 954 ) / Subscribers: 0 | What's this?