This is one of the basic techniques to spot AI fakes:
- Correct number of body features (limbs, fingers, eyes…)
- Non-intersecting body features
- Surface continuity (skin, clothes, walls…)
- Eye reflections
- Consistent illumination of features
- Consistent shadows
The “test” they’re trying to fool, is kind of the Turing test: whether humans can tell them apart.
AndrasKrigare@beehaw.org 4 months ago
Looking completely realistic and being able to discern between real and fake are competing goals. If you can discern the difference, then it does not look completely realistic.
I think what they’re alluding to is generative adversarial networks …wikipedia.org/…/Generative_adversarial_network where creating a better discriminator that can detect a good image from bad is how you get a better image.