Sign inGet started
Paper · arXiv

PhysicsSliders: Learning Physical Controls for Audio Foley Generation

Physical properties provide intuitive controls for sounds made by interacting objects. The challenge is to make a generative model respond predictably to these controls, both individually and in combination. We present \method\ (PXS), trained on simulated contact sounds with 15 material, geometry and contact parameters. Two separately trained variants accept direct parameter inputs or numerical captions. PXS controls hardness, size, speed and damping, supports room descriptions and produces spectrally distinct outputs at fixed targets. When controlling damping and size together, specifying thickness improves frequency accuracy and joint target delivery. Measurements from real recordings d...

AuthorsPeiwei Chang, Yongqiang Chen, Yuelan Cheng et al.
Primary categorycs.SD
Published13 October 2026
Last updated at source13 October 2026
cs.SDcs.AIcs.LG
Embed this entry
<iframe src="https://silytics.si/embed/item/077c6463-6462-4f3b-be57-5f41a696058d" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.