Researchers from NVIDIA (in particular Tero Karras) have once again "solved" image generation.
This time, the scientists were able to remove aliasing in the generator. In a nutshell, then the reason for the artifacts was careless signal processing in the CNN resulting in incorrect discretization. The signal could not be accurately reconstructed, which led to unnatural "jerks" noticeable in the video. The authors have modified the generator to prevent these negative sampling effects.
The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales.
The code is not available yet, but I'm sure NVIDIA will release it soon.
Read more about Alias-Free GAN here.
This time, the scientists were able to remove aliasing in the generator. In a nutshell, then the reason for the artifacts was careless signal processing in the CNN resulting in incorrect discretization. The signal could not be accurately reconstructed, which led to unnatural "jerks" noticeable in the video. The authors have modified the generator to prevent these negative sampling effects.
The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales.
The code is not available yet, but I'm sure NVIDIA will release it soon.
Read more about Alias-Free GAN here.
tg-me.com/gradientdude/324
Create:
Last Update:
Last Update:
Researchers from NVIDIA (in particular Tero Karras) have once again "solved" image generation.
This time, the scientists were able to remove aliasing in the generator. In a nutshell, then the reason for the artifacts was careless signal processing in the CNN resulting in incorrect discretization. The signal could not be accurately reconstructed, which led to unnatural "jerks" noticeable in the video. The authors have modified the generator to prevent these negative sampling effects.
The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales.
The code is not available yet, but I'm sure NVIDIA will release it soon.
Read more about Alias-Free GAN here.
This time, the scientists were able to remove aliasing in the generator. In a nutshell, then the reason for the artifacts was careless signal processing in the CNN resulting in incorrect discretization. The signal could not be accurately reconstructed, which led to unnatural "jerks" noticeable in the video. The authors have modified the generator to prevent these negative sampling effects.
The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales.
The code is not available yet, but I'm sure NVIDIA will release it soon.
Read more about Alias-Free GAN here.
BY Gradient Dude
Share with your friend now:
tg-me.com/gradientdude/324