VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ali, Moayed Haji, Bond, Andrew, Birdal, Tolga, Ceylan, Duygu, Karacan, Levent, Erdem, Erkut, Erdem, Aykut
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913725863165952
author Ali, Moayed Haji
Bond, Andrew
Birdal, Tolga
Ceylan, Duygu
Karacan, Levent
Erdem, Erkut
Erdem, Aykut
author_facet Ali, Moayed Haji
Bond, Andrew
Birdal, Tolga
Ceylan, Duygu
Karacan, Levent
Erdem, Erkut
Erdem, Aykut
contents We propose $\textbf{VidStyleODE}$, a spatiotemporally continuous disentangled $\textbf{Vid}$eo representation based upon $\textbf{Style}$GAN and Neural-$\textbf{ODE}$s. Effective traversal of the latent space learned by Generative Adversarial Networks (GANs) has been the basis for recent breakthroughs in image editing. However, the applicability of such advancements to the video domain has been hindered by the difficulty of representing and controlling videos in the latent space of GANs. In particular, videos are composed of content (i.e., appearance) and complex motion components that require a special mechanism to disentangle and control. To achieve this, VidStyleODE encodes the video content in a pre-trained StyleGAN $\mathcal{W}_+$ space and benefits from a latent ODE component to summarize the spatiotemporal dynamics of the input video. Our novel continuous video generation process then combines the two to generate high-quality and temporally consistent videos with varying frame rates. We show that our proposed method enables a variety of applications on real videos: text-guided appearance manipulation, motion manipulation, image animation, and video interpolation and extrapolation. Project website: https://cyberiada.github.io/VidStyleODE
format Preprint
id arxiv_https___arxiv_org_abs_2304_06020
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
Ali, Moayed Haji
Bond, Andrew
Birdal, Tolga
Ceylan, Duygu
Karacan, Levent
Erdem, Erkut
Erdem, Aykut
Computer Vision and Pattern Recognition
We propose $\textbf{VidStyleODE}$, a spatiotemporally continuous disentangled $\textbf{Vid}$eo representation based upon $\textbf{Style}$GAN and Neural-$\textbf{ODE}$s. Effective traversal of the latent space learned by Generative Adversarial Networks (GANs) has been the basis for recent breakthroughs in image editing. However, the applicability of such advancements to the video domain has been hindered by the difficulty of representing and controlling videos in the latent space of GANs. In particular, videos are composed of content (i.e., appearance) and complex motion components that require a special mechanism to disentangle and control. To achieve this, VidStyleODE encodes the video content in a pre-trained StyleGAN $\mathcal{W}_+$ space and benefits from a latent ODE component to summarize the spatiotemporal dynamics of the input video. Our novel continuous video generation process then combines the two to generate high-quality and temporally consistent videos with varying frame rates. We show that our proposed method enables a variety of applications on real videos: text-guided appearance manipulation, motion manipulation, image animation, and video interpolation and extrapolation. Project website: https://cyberiada.github.io/VidStyleODE
title VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.06020