Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity
This addresses the challenge of unnatural synchronization artifacts in video-to-audio generation for applications like video editing and virtual reality, representing an incremental improvement by integrating existing components.
The paper tackles the problem of generating synchronized audio from video by proposing MaskVAT, a model that combines a high-quality audio codec with a masked generative transformer, achieving highly synchronized results while maintaining competitive audio quality with state-of-the-art methods.
Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are aligned with them, otherwise unnatural synchronization artifacts arise. Recent works have explored the progression of conditioning sound generators on still images and then video features, focusing on quality and semantic matching while ignoring synchronization, or by sacrificing some amount of quality to focus on improving synchronization only. In this work, we propose a V2A generative model, named MaskVAT, that interconnects a full-band high-quality general audio codec with a sequence-to-sequence masked generative model. This combination allows modeling both high audio quality, semantic matching, and temporal synchronicity at the same time. Our results show that, by combining a high-quality codec with the proper pre-trained audio-visual features and a sequence-to-sequence parallel structure, we are able to yield highly synchronized results on one hand, whilst being competitive with the state of the art of non-codec generative audio models. Sample videos and generated audios are available at https://maskvat.github.io .