video-edit-gan.github.io - Temporally Consistent Semantic Video Editing

home > domains > video-edit-gan.github.io

Description: Our work focuses on GAN-based, temporally consistent video editing.

video editing (1401) video consistency (2) gan editing (1)

Example domain paragraphs

Font Awesome fontawesome.com --> arXiv Code Abstract 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

Our method can be applied to diverse videos from the Internet. We can edit it with available in-domain editing methods, e.g., InterfaceGAN, StyleCLIP.

Our method can also be applied to Out-of-domain editing. We show the results on RAVDESS data below. The Out-of-domain editing is StyleGAN-NADA.

Links to video-edit-gan.github.io (4)

• jbhuang0604.github.io Jia-Bin Huang
• twizwei.github.io Yiran Xu
• badouralbahar.github.io Badour AlBahar
• jiabinhuang.com 琼中坑猎物流有限公司