taegyeong-lee/Generating-Realistic-Images-from-In-the-wild-Sounds

Official Code Repository for the paper "Generating Realistic Images from In-the-wild Sounds", ICCV 2023

21
/ 100
Experimental

This project helps creative professionals, marketers, and researchers visualize abstract soundscapes or specific audio events. By inputting any "in-the-wild" sound, such as ambient noise or distinct audio cues, it generates realistic images that visually represent the sound's characteristics. This is ideal for anyone needing to create visual content inspired directly by audio.

No commits in the last 6 months.

Use this if you need to generate unique visual representations or concept art directly from diverse sound files, beyond simple sound wave visualizations.

Not ideal if you are looking for a plug-and-play solution, as it currently requires some technical setup and configuration.

sound-visualization creative-asset-generation multimedia-content-creation audio-description sensory-design
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Jupyter Notebook

License

Last pushed

Aug 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/taegyeong-lee/Generating-Realistic-Images-from-In-the-wild-Sounds"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.