Deep Feature Interpolation for Image Content Changes
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)(2017)
摘要
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.
更多查看译文
关键词
image content changes,datadriven baseline,automatic high-resolution image transformation,deep convolutional features,high-level semantic transformations,image transformation tasks,deep learning,linear interpolation,deep feature interpolation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络