Stitch it in Time: GAN-Based Facial Editing of Real Videos. (arXiv:2201.08361v1 [cs.CV])

The ability of Generative Adversarial Networks to encode rich semantics
within their latent space has been widely adopted for facial image editing.
However, 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. The source video is already temporally coherent,
and deviations from this state arise in part due to careless treatment of
individual …

arxiv cv gan time videos