Jeffrey Zhang - Academia.edu (original) (raw)

Uploads

Papers by Jeffrey Zhang

Research paper thumbnail of Generalized Latent Variable Recovery for Generative Adversarial Networks

ArXiv, 2018

The Generator of a Generative Adversarial Network (GAN) is trained to transform latent vectors dr... more The Generator of a Generative Adversarial Network (GAN) is trained to transform latent vectors drawn from a prior distribution into realistic looking photos. These latent vectors have been shown to encode information about the content of their corresponding images. Projecting input images onto the latent space of a GAN is non-trivial, but previous work has successfully performed this task for latent spaces with a uniform prior. We extend these techniques to latent spaces with a Gaussian prior, and demonstrate our technique's effectiveness.

Research paper thumbnail of Generalized Latent Variable Recovery for Generative Adversarial Networks

ArXiv, 2018

The Generator of a Generative Adversarial Network (GAN) is trained to transform latent vectors dr... more The Generator of a Generative Adversarial Network (GAN) is trained to transform latent vectors drawn from a prior distribution into realistic looking photos. These latent vectors have been shown to encode information about the content of their corresponding images. Projecting input images onto the latent space of a GAN is non-trivial, but previous work has successfully performed this task for latent spaces with a uniform prior. We extend these techniques to latent spaces with a Gaussian prior, and demonstrate our technique's effectiveness.

Log In