Readme
…
Model description
This is the official implementation of “Deep Flexible Structure Preserving Image Smoothing”, which appeared in ACM Multimedia 2022.
Smoothing Level = 0
means the model will try its best to smooth out all the texture, while Smoothing Level = 1
is nearly the same as input.
Images are preprocessed with torchvision.transforms.Resize(640)
before fed into the network.
…