Deep Flexible Structure-preserving Image Smoothing

  • Public
  • 1.7K runs

Run time and cost

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 2 seconds. The predict time for this model varies significantly based on the inputs.


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. …