Download presentation
Presentation is loading. Please wait.
1
Matting and Transparency 15-463: Computational Photography Alexei Efros, CMU, Fall 2006
2
Midterm Statistics
3
Semi-transparent mattes What we really want is to obtain a true alpha matte, which involves semi-transparency Alpha between 0 and 1
4
Matting Problem: Mathematical Definition
5
Why is general matting hard?
6
Solution #1: No Blue!
7
Solution #2: Gray or Flesh
8
Triangulation Matting (Smith & Blinn) How many equations? How many unknowns? Does the background need to be constant color?
9
The Algorithm
10
Triangulation Matting Examples
11
More Examples
12
More examples
13
Problems with Matting Images do not look realistic Lack of Refracted Light Lack of Reflected Light Solution: Modify the Matting Equation
14
Environment Matting and Compositing slides by Jay Hetler Douglas E. Zongker ~ Dawn M. Werner ~ Brian Curless ~ David H. Salsin
15
Environment Matting Equation C = F + (1- )B + C ~ Color F ~ Foreground color B ~ Background color ~ Amount of light that passes through the foreground ~ Contribution of light from Environment that travels through the object
16
Explanation of R – reflectance image T – Texture image
17
Environment Mattes
18
Performance Calibration Matting: 10-20 minutes extraction time for each texture map (Pentium II 400Mhz) Compositing: 4-40 frames per second Real-Time?
19
How much better is Environment Matting? Alpha Matte Environment Matte Photograph
20
How much better is Environment Matting? Alpha Matte Environment Matte Photograph
21
Movies!
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.