The field of visual computing is rapidly advancing due to the emergence of generative
artificial intelligence (AI), which unlocks unprecedented capabilities for the generation …

The evolution of diffusion models has greatly impacted video generation and understanding.
Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the …

We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video
editing without relying on any supervised video editing data. To develop EVE we separately …

We introduce Videoshop, a training-free video editing algorithm for localized semantic edits.
Videoshop allows users to use any editing software, including Photoshop and generative …

Video generation primarily aims to model authentic and customized motion across frames,
making understanding and controlling the motion a crucial topic. Most diffusion-based …

The remarkable generative capabilities of diffusion models have motivated extensive
research in both image and video editing. Compared to video editing which faces additional …

We study the problem of precisely swapping objects in videos, with a focus on those
interacted with by hands, given one user-provided reference object image. Despite the great …

Diffusion Models are popular generative modeling methods in various vision tasks, attracting
significant attention. They can be considered a unique instance of self-supervised learning …

Despite significant advancements in video generation and editing using diffusion models,
achieving accurate and localized video editing remains a substantial challenge …

Existing diffusion-based video editing methods have achieved impressive results in motion
editing. Most of the existing methods focus on the motion alignment between the edited …