Acoustic Field Video for Multimodal Scene Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Daehwa, Harrison, Chris
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917220283580416
author Kim, Daehwa
Harrison, Chris
author_facet Kim, Daehwa
Harrison, Chris
contents We introduce and explore a new multimodal input representation for vision-language models: acoustic field video. Unlike conventional video (RGB with stereo/mono audio), our video stream provides a spatially grounded visualization of sound intensity across a scene, offering a new and powerful dimension of perceptual understanding. Our real-time pipeline uses low-cost beamforming microphone arrays that are already common in smart speakers and increasingly present in robotics and XR headsets, yet this sensing capability remains unutilized for scene understanding. To assess the value of spatial acoustic information, we constructed an evaluation set of 402 question-answer scenes, comparing a state-of-the-art VLM given conventional video with and without paired acoustic field video. Results show a clear and consistent improvement when incorporating spatial acoustic data; the VLM we test improves from 38.3% correct to 67.4%. Our findings highlight that many everyday scene understanding tasks remain underconstrained when relying solely on visual and audio input, and that acoustic field data provides a promising and practical direction for multimodal reasoning. A video demo is available at https://daehwakim.com/seeingsound
format Preprint
id arxiv_https___arxiv_org_abs_2601_17123
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Acoustic Field Video for Multimodal Scene Understanding
Kim, Daehwa
Harrison, Chris
Human-Computer Interaction
Computer Vision and Pattern Recognition
Robotics
We introduce and explore a new multimodal input representation for vision-language models: acoustic field video. Unlike conventional video (RGB with stereo/mono audio), our video stream provides a spatially grounded visualization of sound intensity across a scene, offering a new and powerful dimension of perceptual understanding. Our real-time pipeline uses low-cost beamforming microphone arrays that are already common in smart speakers and increasingly present in robotics and XR headsets, yet this sensing capability remains unutilized for scene understanding. To assess the value of spatial acoustic information, we constructed an evaluation set of 402 question-answer scenes, comparing a state-of-the-art VLM given conventional video with and without paired acoustic field video. Results show a clear and consistent improvement when incorporating spatial acoustic data; the VLM we test improves from 38.3% correct to 67.4%. Our findings highlight that many everyday scene understanding tasks remain underconstrained when relying solely on visual and audio input, and that acoustic field data provides a promising and practical direction for multimodal reasoning. A video demo is available at https://daehwakim.com/seeingsound
title Acoustic Field Video for Multimodal Scene Understanding
topic Human-Computer Interaction
Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2601.17123