Year: 2023
Type: preprint
Abstract: Controlled data generation with GANs is desirable but challenging due to the nonlinearity and high dimensionality of their latent spaces. In this work, we explore image manipulations learned by GANSpace, a state-of-the-art method based on PCA. Through quantitative and qualitative assessments we show: (a) GANSpace produces a wide range of high-quality image manipulations, but they can be highly entangled, limiting potential use cases; (b) Replacing PCA with ICA improves the quality and disentanglement of manipulations; (c) The quality of the generated images can be sensitive to the size of GANs, but regardless of their complexity, fundamental controlling directions can be observed in their latent spaces.
Source: arXiv (Cornell University)
Institutions: Innopolis University, University of Hull
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4378510294