Temporally Consistent Semantic Video Editing
This addresses video editing quality for users of generative models, but is incremental as it builds on existing GAN inversion techniques.
The paper tackles the problem of temporal flickering artifacts in GAN-based video editing by minimizing photometric inconsistency, showing favorable results against baselines.
Generative adversarial networks (GANs) have demonstrated impressive image generation quality and semantic editing capability of real images, e.g., changing object classes, modifying attributes, or transferring styles. However, applying these GAN-based editing to a video independently for each frame inevitably results in temporal flickering artifacts. We present a simple yet effective method to facilitate temporally coherent video editing. Our core idea is to minimize the temporal photometric inconsistency by optimizing both the latent code and the pre-trained generator. We evaluate the quality of our editing on different domains and GAN inversion techniques and show favorable results against the baselines.