Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices

TL;DR

Slicedit introduces a novel video editing approach using spatiotemporal slices and pretrained text-to-image diffusion models to achieve consistent, structure-preserving edits guided by text, overcoming challenges of nonrigid motion.

Contribution

It proposes a new method that applies T2I diffusion models on spatiotemporal slices for zero-shot video editing, enhancing temporal consistency without explicit correspondence mechanisms.

Findings

Effective editing of real-world videos with preserved motion and structure

Outperforms existing methods in temporal consistency and editing quality

Works across diverse video content and editing tasks

Abstract

Text-to-image (T2I) diffusion models achieve state-of-the-art results in image synthesis and editing. However, leveraging such pretrained models for video editing is considered a major challenge. Many existing works attempt to enforce temporal consistency in the edited video through explicit correspondence mechanisms, either in pixel space or between deep features. These methods, however, struggle with strong nonrigid motion. In this paper, we introduce a fundamentally different approach, which is based on the observation that spatiotemporal slices of natural videos exhibit similar characteristics to natural images. Thus, the same T2I diffusion model that is normally used only as a prior on video frames, can also serve as a strong prior for enhancing temporal consistency by applying it on spatiotemporal slices. Based on this observation, we present Slicedit, a method for text-based video editing that utilizes a pretrained T2I diffusion model to process both spatial and spatiotemporal slices. Our method generates videos that retain the structure and motion of the original video while adhering to the target text. Through extensive experiments, we demonstrate Slicedit's ability to edit a wide range of real-world videos, confirming its clear advantages compared to existing competing methods. Webpage: https://matankleiner.github.io/slicedit/