SoundBrush: Sound as a Brush for Visual Scene Editing
This addresses the problem of intuitive, sound-guided visual editing for users in creative and multimedia applications, though it is incremental as it builds on existing image-editing and generative models.
The authors tackled the problem of editing visual scenes using sound as guidance, proposing SoundBrush, a model that extends Latent Diffusion Models to incorporate audio information, enabling accurate manipulation of scenery or insertion of sounding objects while preserving original content, with demos showing diverse in-the-wild sound-driven edits.
We propose SoundBrush, a model that uses sound as a brush to edit and manipulate visual scenes. We extend the generative capabilities of the Latent Diffusion Model (LDM) to incorporate audio information for editing visual scenes. Inspired by existing image-editing works, we frame this task as a supervised learning problem and leverage various off-the-shelf models to construct a sound-paired visual scene dataset for training. This richly generated dataset enables SoundBrush to learn to map audio features into the textual space of the LDM, allowing for visual scene editing guided by diverse in-the-wild sound. Unlike existing methods, SoundBrush can accurately manipulate the overall scenery or even insert sounding objects to best match the audio inputs while preserving the original content. Furthermore, by integrating with novel view synthesis techniques, our framework can be extended to edit 3D scenes, facilitating sound-driven 3D scene manipulation. Demos are available at https://soundbrush.github.io/.