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

Kang Zhang, Trung X. Pham, Suyeon Lee, Axi Niu, Arda Senocak, Joon Son Chung

Keywords: Open domain video to audio generation, FLow based model, Cross modal alignment, Transformer denoiser, Model guided training

TL;DR: We introduce MGAudio, a flow-based framework for video-to-audio generation that leverages model-guided dual-role alignment to achieve state-of-the-art performance.

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 denoiser, (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

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 5331