2020/12/09 by Nurit Spingarn-Eliezer, Spingarn-Eliezer, Nurit, Ron Banner +3
Computer Science · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image Processing and 3D Reconstruction #cs.CV
paper · pdf · doi:10.48550/arxiv.2012.05328
openalex publication_date 2020/12/09 · arxiv created 2021/01/24 · arxiv updated 2021/01/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent research has shown remarkable success in revealing "steering" directions in the latent spaces of pre-trained GANs. These directions correspond to semantically meaningful image transformations e.g., shift, zoom, color manipulations), and have similar interpretable effects across all categories that the GAN can generate. Some methods focus on user-specified transformations, while others discover transformations in an unsupervised manner. However, all existing techniques rely on an optimization procedure to expose those directions, and offer no control over the degree of allowed interaction between different transformations. In this paper, we show that "steering" trajectories can be computed in closed form directly from the generator's weights without any form of training or optimization. This applies to user-prescribed geometric transformations, as well as to unsupervised discovery of more complex effects. Our approach allows determining both linear and nonlinear trajectories, and has many advantages over previous methods. In particular, we can control whether one transformation is allowed to come on the expense of another (e.g. zoom-in with or without allowing translation to keep the object centered). Moreover, we can determine the natural end-point of the trajectory, which corresponds to the largest extent to which a transformation can be applied without incurring degradation. Finally, we show how transferring attributes between images can be achieved without optimization, even across different categories.