Deep Feature Interpolation for Image Content Changes
This provides a simple baseline for evaluating complex image transformation algorithms, addressing challenges in semantic image editing for computer vision researchers.
The paper tackles the problem of automatic high-resolution image transformation by proposing Deep Feature Interpolation (DFI), which uses linear interpolation of pre-trained convolutional features to perform semantic changes like altering age or adding smiles, sometimes matching or outperforming state-of-the-art methods without requiring specialized training.
We propose Deep Feature Interpolation (DFI), a new data-driven baseline for automatic high-resolution image transformation. As the name suggests, it relies only on simple linear interpolation of deep convolutional features from pre-trained convnets. We show that despite its simplicity, DFI can perform high-level semantic transformations like "make older/younger", "make bespectacled", "add smile", among others, surprisingly well - sometimes even matching or outperforming the state-of-the-art. This is particularly unexpected as DFI requires no specialized network architecture or even any deep network to be trained for these tasks. DFI therefore can be used as a new baseline to evaluate more complex algorithms and provides a practical answer to the question of which image transformation tasks are still challenging in the rise of deep learning.