音響フィールド動画によるマルチモーダルなシーン理解
Acoustic Field Video for Multimodal Scene Understanding
ビームフォーミングマイクアレイで音の強度を空間的に可視化した「音響フィールド動画」をVLMに入力し、通常の動画よりシーン理解の正答率が38.3%から67.4%に向上することを示した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Daehwa Kim, Chris Harrison
分類: cs.HC, cs.CV, cs.RO
原文アブストラクト
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
