Learning Visual Styles from Audio-Visual Associations

Tingle Li
Yichen Liu
Andrew Owens
Hang Zhao

Audio-driven image stylization. We manipulate the style of an image to match a sound. After training with an unlabeled dataset of egocentric hiking videos, our model learns visual styles for a variety of ambient sounds, such as light and heavy rain, as well as physical interactions, such as footsteps.


From the patter of rain to the crunch of snow, the sounds we hear often reveal the visual textures within a scene. In this paper, we present a method for learning visual styles from paired audio-visual data. Our model learns to manipulate the texture of a scene to match a sound, a problem we term audio-driven image stylization . Given a dataset of paired, unlabeled audio-visual data, the model learns to manipulate input images such that, after manipulation, they are more likely to co-occur with other input sounds. In quantitative and qualitative evaluations, our sound-based model outperforms label-based approaches. We also use audio as an intuitive embedding space for image manipulation, and show that manipulating audio, such as by adjusting its volume, results in predictable visual changes.

Results Video










 [Download Link] (coming soon)

Audio-driven Image Stylization Results

Input Image
Output Image 1
Output Image 2

Restyling Video by Manipulating its Sound

  Input Video
  120% Volume
  140% Volume
  160% Volume

  Input Video
  40% Volume
  80% Volume
  120% Volume

Varying Sound Volume Results

Input Image
30% Volume
60% Volume
90% Volume

Mixing Sound Results

Input Image
Sound 1
Sound 2
Mixture Sound

Paper and Supplementary Material

Tingle Li, Yichen Liu, Andrew Owens, Hang Zhao
Learning Visual Styles from Audio-Visual Associations
arXiv preprint



This template was originally made by Phillip Isola and Richard Zhang for a colorful ECCV project; the code can be found here.