Generative Adversarial Networks for Face Manipulation in Videos

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Stitch it in Time: GAN-Based Facial Editing of Real Videos

The ability of generative adversarial networks to encode rich semantics within their latent space has been widely adopted for facial image editing, but replicating their success with videos has proven challenging.

Sets of high-quality facial videos are lacking, and working with videos introduces a fundamental barrier to overcome-temporal coherency.

We propose that this barrier is largely artificial, and demonstrate that deviations from this state arise in part due to careless treatment of individual components in the editing pipeline.

We draw on these insights and propose a framework for semantic editing of faces in videos, demonstrating significant improvements over the current state-of-the-art.

Our method produces meaningful face manipulations, maintains a higher degree of temporal consistency, and can be applied to challenging, high quality, talking head videos which current methods struggle with.

Authors

Rotem Tzaban, Ron Mokady, Rinon Gal, Amit H. Bermano, Daniel Cohen-Or

◐ Recommended Follows

◐ Latest Activity