StereoFoley: Object-Aware Stereo Audio Generation from Video
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913041311858688 |
|---|---|
| author | Karchkhadze, Tornike Chen, Kuan-Lin Heydari, Mojtaba Henzel, Robert Toso, Alessandro Souden, Mehrez Atkins, Joshua |
| author_facet | Karchkhadze, Tornike Chen, Kuan-Lin Heydari, Mojtaba Henzel, Robert Toso, Alessandro Souden, Mehrez Atkins, Joshua |
| contents | We present StereoFoley, a video-to-audio generation framework that produces semantically aligned, temporally synchronized, and spatially accurate stereo sound at 48 kHz. While recent generative video-to-audio models achieve strong semantic and temporal fidelity, they largely remain limited to mono or fail to deliver object-aware stereo imaging, constrained by the lack of professionally mixed, spatially accurate video-to-audio datasets. First, we develop a base model that generates stereo audio from video, achieving performance on par with state-of-the-art V2A models in both semantic accuracy and synchronization. Next, to overcome dataset limitations, we introduce a synthetic data generation pipeline that combines video analysis, object tracking, and audio synthesis with dynamic panning and distance-based loudness controls, enabling spatially accurate object-aware sound. Finally, we fine-tune the base model on this synthetic dataset, yielding clear object-audio correspondence. Since no established metrics exist, we introduce a stereo object-awareness metric and report it alongside a human listening study; the two evaluations exhibit consistent trends. This work establishes the first end-to-end framework for stereo object-aware video-to-audio generation, addressing a critical gap in the field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18272 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StereoFoley: Object-Aware Stereo Audio Generation from Video Karchkhadze, Tornike Chen, Kuan-Lin Heydari, Mojtaba Henzel, Robert Toso, Alessandro Souden, Mehrez Atkins, Joshua Sound Multimedia Audio and Speech Processing We present StereoFoley, a video-to-audio generation framework that produces semantically aligned, temporally synchronized, and spatially accurate stereo sound at 48 kHz. While recent generative video-to-audio models achieve strong semantic and temporal fidelity, they largely remain limited to mono or fail to deliver object-aware stereo imaging, constrained by the lack of professionally mixed, spatially accurate video-to-audio datasets. First, we develop a base model that generates stereo audio from video, achieving performance on par with state-of-the-art V2A models in both semantic accuracy and synchronization. Next, to overcome dataset limitations, we introduce a synthetic data generation pipeline that combines video analysis, object tracking, and audio synthesis with dynamic panning and distance-based loudness controls, enabling spatially accurate object-aware sound. Finally, we fine-tune the base model on this synthetic dataset, yielding clear object-audio correspondence. Since no established metrics exist, we introduce a stereo object-awareness metric and report it alongside a human listening study; the two evaluations exhibit consistent trends. This work establishes the first end-to-end framework for stereo object-aware video-to-audio generation, addressing a critical gap in the field. |
| title | StereoFoley: Object-Aware Stereo Audio Generation from Video |
| topic | Sound Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.18272 |