Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

TL;DR

This paper introduces a zero-shot, text-guided video translation framework that adapts image diffusion models to generate temporally consistent videos without re-training, leveraging hierarchical constraints and patch matching.

Contribution

It presents a novel two-part framework for video translation that ensures temporal coherence using hierarchical constraints and patch matching, compatible with existing diffusion models.

Findings

Achieves high-quality, temporally-coherent videos

Operates without re-training or optimization

Compatible with existing diffusion techniques

Abstract

Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.