VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling
This addresses the problem of generating contextually appropriate music for videos, such as in movie trailers or advertisements, but is incremental as it builds on existing video-conditioned generation methods.
The paper tackles video-to-music generation by proposing VidMuse, a framework that uses long-short-term modeling to create music aligned with video inputs, achieving high-fidelity results and outperforming existing models in audio quality, diversity, and alignment.
In this work, we systematically study music generation conditioned solely on the video. First, we present a large-scale dataset comprising 360K video-music pairs, including various genres such as movie trailers, advertisements, and documentaries. Furthermore, we propose VidMuse, a simple framework for generating music aligned with video inputs. VidMuse stands out by producing high-fidelity music that is both acoustically and semantically aligned with the video. By incorporating local and global visual cues, VidMuse enables the creation of musically coherent audio tracks that consistently match the video content through Long-Short-Term modeling. Through extensive experiments, VidMuse outperforms existing models in terms of audio quality, diversity, and audio-visual alignment. The code and datasets are available at https://vidmuse.github.io/.