The Sound of Water: Inferring Physical Properties From Pouring Liquids
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-09 · 48 (9) · 11111-11123
DOI: 10.1109/tpami.2026.3690989 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-09. Verfasst von Piyush Bagad und 3 weiteren Autor:innen. Die Arbeit nennt 100 Literaturangaben. Gefördert von: EPSRC Programme, Royal Society Research Professorship.
Abstract (Originalsprache)
We study the connection between audio observations and the underlying physics of a mundane yet intriguing everyday activity: pouring liquids. Given only the sound of liquid pouring into a container, our objective is to automatically infer physical properties such as the liquid level, the shape and size of the container, the pouring rate and the time to fill. To this end, we: (i) show in theory that these properties can be determined from the fundamental frequency (pitch); (ii) train a pitch detection model with supervision from simulated data and visual data with a physics-inspired objective; (iii) introduce a new large dataset of real pouring videos for a systematic study; (iv) show that the trained model can indeed infer these physical properties for real data; and finally, (v) we demonstrate strong generalization to various container shapes, other datasets, and in-the-wild YouTube videos. Our work presents a keen understanding of a narrow yet rich problem at the intersection of acoustics, physics, and learning. It opens up applications to enhance multisensory perception in robotic pouring.
Förderung
- EPSRC Programme
- Royal Society Research Professorship
Zitieren
APA
Bagad, P., Tapaswi, M., Snoek, C. G. M., & Zisserman, A. (2026). The Sound of Water: Inferring Physical Properties From Pouring Liquids. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(9), 11111-11123. https://doi.org/10.1109/tpami.2026.3690989
Vancouver
Bagad P, Tapaswi M, Snoek CGM, Zisserman A. The Sound of Water: Inferring Physical Properties From Pouring Liquids. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(9):11111-11123. doi:10.1109/tpami.2026.3690989
BibTeX
@article{Bagad2026,
author = {Bagad, Piyush and Tapaswi, Makarand and Snoek, Cees G M and Zisserman, Andrew},
title = {The Sound of Water: Inferring Physical Properties From Pouring Liquids},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {9},
pages = {11111--11123},
doi = {10.1109/tpami.2026.3690989}
}
EUVIMED