Deep Feature Interpolation for Image Content Changes

Paul Upchurch, Jacob Gardner, Geoff Pleiss, Robert Pless, Noah Snavely, Kavita Bala, Kilian Weinberger; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 7064-7073

Abstract


We propose Deep Feature Interpolation (DFI), a new data- driven baseline for automatic high-resolution image transformation. As the name suggests, DFI 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 after the advent of deep learning.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Upchurch_2017_CVPR,
author = {Upchurch, Paul and Gardner, Jacob and Pleiss, Geoff and Pless, Robert and Snavely, Noah and Bala, Kavita and Weinberger, Kilian},
title = {Deep Feature Interpolation for Image Content Changes},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}