Why are hands difficult for ai images?

1.21K views

Why are hands difficult for ai images?

In: 250

63 Answers

1 2 3 6 7
Anonymous 0 Comments

Hands are complex things… They bend in specific but varied ways.

But more importantly, AIs can only handle what they’re trained on. Creating images, they were never properly controlled for building their own images of hands and having them judged as being correct. So without guidance they don’t necessarily learn what you think they learn.

AIs “learn” by being re-wired bit by bit and subjected to testing, with the goal to raise the test score of the AI over time as you figure out which re-wire attempts produce positive or negative effects. But the “teacher” administering the test is also just a bot, and it isn’t scoring the test the way humans necessarily think it should be.

Anonymous 0 Comments

An AI is not a mind. In essence it is a pattern-matching algorithm that is trained on images and gains a model of what things tend to accompany each other in a lot of images. For example the AI doesn’t know what a tree is but it can learn that images of leaves tend to be clustered in certain ways associated with a trunk and with a particular orientation to the ground, etc.

Since it is all a big combination of matched patterns without any real understanding of what the patterns are, hands are a significant problem. Fingers tend to appear in images near other fingers, but their orientation with regard to each other varies significantly. Furthermore the number of fingers which are visible in a given image can vary as well, since many positions of the hand block the view of some of the fingers. The number of fingers is also very precise; only 5 per hand, no more and no less.

With that in mind it is very easy to spot something odd when AI is creating an image of hands. Nobody is going to notice if a tree has an unusually high or low number of leaves as there isn’t particular number to hit. Also the orientation of leaves can vary significantly and the tree will still look acceptable, but not so for fingers.

Anonymous 0 Comments

Hands are complex things… They bend in specific but varied ways.

But more importantly, AIs can only handle what they’re trained on. Creating images, they were never properly controlled for building their own images of hands and having them judged as being correct. So without guidance they don’t necessarily learn what you think they learn.

AIs “learn” by being re-wired bit by bit and subjected to testing, with the goal to raise the test score of the AI over time as you figure out which re-wire attempts produce positive or negative effects. But the “teacher” administering the test is also just a bot, and it isn’t scoring the test the way humans necessarily think it should be.

Anonymous 0 Comments

An AI is not a mind. In essence it is a pattern-matching algorithm that is trained on images and gains a model of what things tend to accompany each other in a lot of images. For example the AI doesn’t know what a tree is but it can learn that images of leaves tend to be clustered in certain ways associated with a trunk and with a particular orientation to the ground, etc.

Since it is all a big combination of matched patterns without any real understanding of what the patterns are, hands are a significant problem. Fingers tend to appear in images near other fingers, but their orientation with regard to each other varies significantly. Furthermore the number of fingers which are visible in a given image can vary as well, since many positions of the hand block the view of some of the fingers. The number of fingers is also very precise; only 5 per hand, no more and no less.

With that in mind it is very easy to spot something odd when AI is creating an image of hands. Nobody is going to notice if a tree has an unusually high or low number of leaves as there isn’t particular number to hit. Also the orientation of leaves can vary significantly and the tree will still look acceptable, but not so for fingers.

Anonymous 0 Comments

Because hands are difficult for humans to draw.

Most artists find drawing hands difficult because of all the small joints that have to be positioned just right to look real.

As a result, human made drawings often have badly drawn hands or the hands are hidden.

AI is trained on images made by humans so if humans struggle with something, it will too.

Anonymous 0 Comments

Weirdly enough hands are difficult for your unconscious mind too. One of the easiest ways to determine if you are dreaming is to look at your hands.

Anonymous 0 Comments

Because hands are difficult for humans to draw.

Most artists find drawing hands difficult because of all the small joints that have to be positioned just right to look real.

As a result, human made drawings often have badly drawn hands or the hands are hidden.

AI is trained on images made by humans so if humans struggle with something, it will too.

Anonymous 0 Comments

Weirdly enough hands are difficult for your unconscious mind too. One of the easiest ways to determine if you are dreaming is to look at your hands.

Anonymous 0 Comments

Hands are complex things… They bend in specific but varied ways.

But more importantly, AIs can only handle what they’re trained on. Creating images, they were never properly controlled for building their own images of hands and having them judged as being correct. So without guidance they don’t necessarily learn what you think they learn.

AIs “learn” by being re-wired bit by bit and subjected to testing, with the goal to raise the test score of the AI over time as you figure out which re-wire attempts produce positive or negative effects. But the “teacher” administering the test is also just a bot, and it isn’t scoring the test the way humans necessarily think it should be.

Anonymous 0 Comments

Teeth, when smiling, is tough for AI too, the results are quite disturbing! Toooo many teeeth

1 2 3 6 7