TVG: A Training-free Transition Video Generation Method with Diffusion Models

TL;DR

This paper introduces TVG, a training-free diffusion-based method for generating smooth transition videos, utilizing Gaussian Process Regression and novel architectural components to improve temporal coherence without additional training.

Contribution

The paper presents a novel training-free transition video generation approach using diffusion models, Gaussian Process Regression, and new architectural designs for enhanced temporal control.

Findings

Effective generation of high-quality transition videos

Smooth and coherent frame transitions achieved

No additional training required for the diffusion models

Abstract

Transition videos play a crucial role in media production, enhancing the flow and coherence of visual narratives. Traditional methods like morphing often lack artistic appeal and require specialized skills, limiting their effectiveness. Recent advances in diffusion model-based video generation offer new possibilities for creating transitions but face challenges such as poor inter-frame relationship modeling and abrupt content changes. We propose a novel training-free Transition Video Generation (TVG) approach using video-level diffusion models that addresses these limitations without additional training. Our method leverages Gaussian Process Regression ($\mathcal{GPR}$) to model latent representations, ensuring smooth and dynamic transitions between frames. Additionally, we introduce interpolation-based conditional controls and a Frequency-aware Bidirectional Fusion (FBiF) architecture to enhance temporal control and transition reliability. Evaluations of benchmark datasets and custom image pairs demonstrate the effectiveness of our approach in generating high-quality smooth transition videos. The code are provided in https://sobeymil.github.io/tvg.com.