FaceCook: Face Generation Based on Linear Scaling Factors
This work addresses a specific issue in face generation for computer vision applications, presenting an incremental improvement over existing editing techniques.
The paper tackles the problem of artifacts and incorrect feature rendering in face image editing by proposing a method that maps latent vectors to scaling factors via multivariate linear equations, resulting in improved image diversity and greater time efficiency compared to baseline approaches.
With the excellent disentanglement properties of state-of-the-art generative models, image editing has been the dominant approach to control the attributes of synthesised face images. However, these edited results often suffer from artifacts or incorrect feature rendering, especially when there is a large discrepancy between the image to be edited and the desired feature set. Therefore, we propose a new approach to mapping the latent vectors of the generative model to the scaling factors through solving a set of multivariate linear equations. The coefficients of the equations are the eigenvectors of the weight parameters of the pre-trained model, which form the basis of a hyper coordinate system. The qualitative and quantitative results both show that the proposed method outperforms the baseline in terms of image diversity. In addition, the method is much more time-efficient because you can obtain synthesised images with desirable features directly from the latent vectors, rather than the former process of editing randomly generated images requiring many processing steps.