Do we need to fit a network for every image?

vsitzmann / siren

Official implementation of "Implicit Neural Representations with Periodic Activation Functions"

MIT License

1.72k stars 247 forks source link

Do we need to fit a network for every image? #45

Closed cwchenwang closed 3 years ago

cwchenwang commented 3 years ago

I found when fitting an image for SIREN, we only input a position encoding (doesn't contain the information of the image) and backdrop by comparing the output with the ground truth image. Does that mean we will input the same tensors (linear space from -1 to 1) when fitting different images? If so, the network parameters will be different for every image.