Find Paper, Faster
Example:10.1021/acsami.1c06204 or Chem. Rev., 2007, 107, 2411-2502
StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows
ACM Transactions on Graphics   (IF6.495),  Pub Date : 2021-05-06, DOI: 10.1145/3447648
Rameen Abdal, Peihao Zhu, Niloy J. Mitra, Peter Wonka

High-quality, diverse, and photorealistic images can now be generated by unconditional GANs (e.g., StyleGAN). However, limited options exist to control the generation process using (semantic) attributes while still

preserving the quality of the output. Further, due to the entangled nature of the GAN latent space, performing edits along one attribute can easily result in unwanted changes along other attributes. In this article, in the context of conditional exploration of entangled latent spaces, we investigate the two sub-problems of attribute-conditioned sampling and attribute-controlled editing. We present StyleFlow as a simple, effective, and robust solution to both the sub-problems by formulating conditional exploration as an instance of conditional continuous normalizing flows in the GAN latent space conditioned by attribute features. We evaluate our method using the face and the car latent space of StyleGAN, and demonstrate fine-grained disentangled edits along various attributes on both real photographs and StyleGAN generated images. For example, for faces, we vary camera pose, illumination variation, expression, facial hair, gender, and age. Finally, via extensive qualitative and quantitative comparisons, we demonstrate the superiority of StyleFlow over prior and several concurrent works. Project Page and Video: