Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [image-super-resolution]

For questions about the super-resolution of images (and videos).

6 questions
4
votes
2 answers

Why is no activation function used at the final layer of super-resolution models?

I'm trying to implement some image super-resolution models on medical images. After reading a set of papers, I found that none of the existing models use any activation function for the last layer. What's the rationale behind that?
Saeed
  • 331
  • 2
  • 9
1
vote
3 answers

Why is AI Super Resolution Reconstruction more than just guessing?

I saw a video on Youtube about AI and Super Resolution Image Reconstruction with TecoGAN. I must say I am impressed. Now, I am wondering how reliable this is. I have learned at university that you lose information if you do not sample to fullfill…
NewToAI2021
  • 43
  • 3
0
votes
0 answers

Can AI/ML be used to decipher unknown text on such a low resolution scale of one or two letters to a pixel by color?

Can an image of unknown text, with resolution of about one or two letters in real life represented by a pixel (like if the image is a photo taken from far away), be used by machine learning or AI to reconstruct the text based on the color of the…
AndroidUser558
  • 1
  • 1
0
votes
0 answers

Which mathematical properties do PSNR and MSE hold?

We know the Structural Similarity Index (SSIM) holds the following properties: Unique maximum: S(x, y) = 1 if and only if x = y Boundedness: S(x, y) ≤ 1 Symmetry: S(x, y) = S(y, x) My question is: do we know simple some properties like these…
Theo Deep
  • 175
  • 1
  • 5
0
votes
0 answers

How to interpret upsampling(deconv, nn, bilinear) as matrices?

I am reading this Distill article Deconvolution and Checkerboard Artifacts about avoiding artifacts in images generated by neural networks. In the section of Better Upsampling, the author compares the difference between deconvolution (i.e.…
JonasW
  • 1
  • 3
0
votes
2 answers

Is Relativistic GAN better than WGAN-GP?

I am currently reading the ESRGAN paper and I noticed that they have used Relativistic GAN for training discriminator. So, is it because Relativistic GAN leads to better results than WGAN-GP?
SANJAY BHANDARI
  • 11
  • 3