Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation

TL;DR

MGAudio introduces a flow-based framework with model-guided dual-role alignment for high-fidelity open-domain video-to-audio generation, significantly improving coherence and realism over previous methods.

Contribution

The paper proposes a novel model-guided dual-role alignment mechanism within a flow-based Transformer framework for video-to-audio generation, outperforming existing guidance techniques.

Findings

Achieves state-of-the-art FAD of 0.40 on VGGSound

Outperforms classifier-free guidance baselines in quality metrics

Generalizes effectively to the UnAV-100 benchmark

Abstract

We present MGAudio, a novel flow-based framework for open-domain video-to-audio generation, which introduces model-guided dual-role alignment as a central design principle. Unlike prior approaches that rely on classifier-based or classifier-free guidance, MGAudio enables the generative model to guide itself through a dedicated training objective designed for video-conditioned audio generation. The framework integrates three main components: (1) a scalable flow-based Transformer model, (2) a dual-role alignment mechanism where the audio-visual encoder serves both as a conditioning module and as a feature aligner to improve generation quality, and (3) a model-guided objective that enhances cross-modal coherence and audio realism. MGAudio achieves state-of-the-art performance on VGGSound, reducing FAD to 0.40, substantially surpassing the best classifier-free guidance baselines, and consistently outperforms existing methods across FD, IS, and alignment metrics. It also generalizes well to the challenging UnAV-100 benchmark. These results highlight model-guided dual-role alignment as a powerful and scalable paradigm for conditional video-to-audio generation. Code is available at: https://github.com/pantheon5100/mgaudio