English

Deep Feature Interpolation for Image Content Changes

Computer Vision and Pattern Recognition 2017-06-20 v2

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.

Keywords

Cite

@article{arxiv.1611.05507,
  title  = {Deep Feature Interpolation for Image Content Changes},
  author = {Paul Upchurch and Jacob Gardner and Geoff Pleiss and Robert Pless and Noah Snavely and Kavita Bala and Kilian Weinberger},
  journal= {arXiv preprint arXiv:1611.05507},
  year   = {2017}
}

Comments

First two authors contributed equally. Accepted by CVPR 2017. Code at https://github.com/paulu/deepfeatinterp

R2 v1 2026-06-22T16:55:05.546Z