Colorization Chapter
The portrait experiment
Summary of the first set of experiments
The value indicated above an experiment is the value of the spatial coherency parameter. Click on an image to zoom. Click on an experiment name to access its personal webpage.
Colors seem to fade when the parameter gets higher. This unexpected bias mostly disappears in the second set of experiments.
| 1 |
400 |
500 |
600 |
700 |
800 |
1000 |
1500 |
2000 |
3000 |
4000 |
10000 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
| 1 |
400 |
500 |
600 |
700 |
800 |
1000 |
1500 |
2000 |
3000 |
4000 |
10000 |
Pick your favourite value of the spatial coherency parameter !
Remember the edges predicted (they don't depend on the parameter) and the original images:
Back to the colorization chapter page,
or forward to the second set of experiments.
Back to the main page
