Yeah but you're assuming that you know how their creating this data. Just throwing an option out there - what if they created a latent space of 3D people and iteratively expanded it with GANs and 2D real image datasets.…
def not for every situation. I was happy to see that these guys weren't starting from medical use-cases. Way too hard.
Cool points - "...original dataset without having access to a critical basis set of the original?" I think that they're not trying to copy existing datasets but are trying to generate new datasets that solve various…
Good points! Most data is def crap lol. I don't see few shot, one-shot or no-shot getting anywhere close to standard supervised learning for anything practical. It really doesn't make sense in production settings at…
I would definitely saw that this is extremely hard to accomplish on one hand and on the other if it works it would be a game changer! A good simulation is the holy grail of AI. It solves the data bottleneck once the…
Yeah but you're assuming that you know how their creating this data. Just throwing an option out there - what if they created a latent space of 3D people and iteratively expanded it with GANs and 2D real image datasets.…
def not for every situation. I was happy to see that these guys weren't starting from medical use-cases. Way too hard.
Cool points - "...original dataset without having access to a critical basis set of the original?" I think that they're not trying to copy existing datasets but are trying to generate new datasets that solve various…
Good points! Most data is def crap lol. I don't see few shot, one-shot or no-shot getting anywhere close to standard supervised learning for anything practical. It really doesn't make sense in production settings at…
I would definitely saw that this is extremely hard to accomplish on one hand and on the other if it works it would be a game changer! A good simulation is the holy grail of AI. It solves the data bottleneck once the…