Surrogate Gradient Field for Latent Space Manipulation
Minjun Li, Yanghua Jin, Huachun Zhu · 2021
Generative adversarial networks (GANs) can generate high-quality images from sampled latent codes. Recent works attempt to edit an image by manipulating its under-lying latent code, but rarely go beyond the basic task of at-tribute adjustment. We propose the first method that enables manipulation with multidimensional condition such as key-points and captions. Specifically, we design an algorithm that searches for a new latent code that satisfies the target condition based on the Surrogate Gradient Field (SGF) induced by an auxiliary mapping network. For quantitative comparison, we propose a metric to evaluate the disentanglement of manipulation methods. Thorough experimental analysis on the facial attribute adjustment task shows that our method outperforms state-of-the-art methods in disentanglement. We further apply our method to tasks of various condition modalities to demonstrate that our method can alter complex image properties such as keypoints and captions.