Deep Feature Interpolation

Deep Feature Interpolation For Image Content Changes

Paul Upchurch1,2, Jacob Gardner1,2, Geoff Pleiss2, Robert Pless3, Noah Snavely2, Kavita Bala2, Kilian Q. Weinberger2
1Authors contributed equally, 2Cornell University, 3George Washington University

CVPR 2017

Download: Paper (9.7 MB), Supplemental (37 MB), Poster (47 MB), Code (GitHub)

Abstract: 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.


@InProceedings{upchurch2017deep, author = {Paul Upchurch and Jacob Gardner and Geoff Pleiss and Robert Pless and Noah Snavely and Kavita Bala and Kilian Q. Weinberger}, title = {Deep Feature Interpolation For Image Content Changes}, booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {July}, year = {2017} }