There are many edge-aware filters varying in their construction forms and filtering properties. It seems impossible to uniformly represent and accelerate them in a single framework. We made the attempt to learn a big and important family of edge-aware operators from data. Our method is based on a deep convolutional neural network with a gradient domain training procedure, which gives rise to a powerful tool to approximate var-ious filters without knowing the original models and implementation details. The only difference among these operators in our system becomes merely the learned parameters. Our system en-ables fast approximation for complex edge-aware filters and achieves up to 200x acceleration, re-gardless of their originally very different imple-mentation. Fast speed can also be achieved when creating new effects using spatially varying filter or filter combination, bearing out the effective-ness of our deep edge-aware filters.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below