Motion-aware Latent Diffusion Models for Video Frame Interpolation

TL;DR

This paper introduces MADiff, a motion-aware latent diffusion model that improves video frame interpolation by effectively incorporating motion priors, resulting in more accurate and visually coherent interpolated frames, especially in complex motion scenarios.

Contribution

The paper presents a novel diffusion-based framework that explicitly models motion priors for enhanced video frame interpolation accuracy.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Significantly outperforms existing methods in dynamic texture scenarios.

Produces visually smooth and realistic interpolated frames.

Abstract

With the advancement of AIGC, video frame interpolation (VFI) has become a crucial component in existing video generation frameworks, attracting widespread research interest. For the VFI task, the motion estimation between neighboring frames plays a crucial role in avoiding motion ambiguity. However, existing VFI methods always struggle to accurately predict the motion information between consecutive frames, and this imprecise estimation leads to blurred and visually incoherent interpolated frames. In this paper, we propose a novel diffusion framework, motion-aware latent diffusion models (MADiff), which is specifically designed for the VFI task. By incorporating motion priors between the conditional neighboring frames with the target interpolated frame predicted throughout the diffusion sampling procedure, MADiff progressively refines the intermediate outcomes, culminating in generating both visually smooth and realistic results. Extensive experiments conducted on benchmark datasets demonstrate that our method achieves state-of-the-art performance significantly outperforming existing approaches, especially under challenging scenarios involving dynamic textures with complex motion.