Unsupervised Projection Networks for Generative Adversarial Networks
UC Berkeley（加州大学伯克利分校）
英文摘要：
We propose the use of unsupervised learning to train projection networks that project onto the latent space of an already trained generator. We apply our method to a trained StyleGAN, and use our projection network to perform image super-resolution and clustering of images into semantically identifiable groups.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
