 |
 |
 |
 |
 |
 |
 |
 |
| • |
Suppose we have a
way to generate realistic
|
|
|
images of faces
from underlying variables that
|
|
describe
emotional expression, lighting, pose,
|
|
|
and facial
characteristics.
|
|
|
| • |
Given a big
database of unlabeled faces, we
|
|
|
|
should be able to
recover the state of the
|
|
|
generator.
|
|