Towards Unified Keyframe Propagation Models

TL;DR

This paper introduces a two-stream model combining local and global interactions to improve keyframe propagation in video editing, especially for high-frequency details, outperforming existing methods in inpainting tasks.

Contribution

The paper proposes a novel two-stream approach that separately handles high-frequency and low-frequency features for more accurate keyframe propagation in videos.

Findings

Improved propagation of high-frequency details in video inpainting.

Achieved 44% and 26% improvements in FID and LPIPS scores.

Robust performance in challenging scenarios like large camera motions.

Abstract

Many video editing tasks such as rotoscoping or object removal require the propagation of context across frames. While transformers and other attention-based approaches that aggregate features globally have demonstrated great success at propagating object masks from keyframes to the whole video, they struggle to propagate high-frequency details such as textures faithfully. We hypothesize that this is due to an inherent bias of global attention towards low-frequency features. To overcome this limitation, we present a two-stream approach, where high-frequency features interact locally and low-frequency features interact globally. The global interaction stream remains robust in difficult situations such as large camera motions, where explicit alignment fails. The local interaction stream propagates high-frequency details through deformable feature aggregation and, informed by the global interaction stream, learns to detect and correct errors of the deformation field. We evaluate our two-stream approach for inpainting tasks, where experiments show that it improves both the propagation of features within a single frame as required for image inpainting, as well as their propagation from keyframes to target frames. Applied to video inpainting, our approach leads to 44% and 26% improvements in FID and LPIPS scores. Code at https://github.com/runwayml/guided-inpainting