Year: 2026
Type: conference-paper
Abstract: 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.
Authors: Tornike Karchkhadze, Kuan-Lin Chen, Mojtaba Heydari, Robert Henzel, Alessandro Toso, Mehrez Souden, Joshua Atkins
Institutions: University of California San Diego, Apple (United States)
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416257609
FWCI:
Cites:
Cited by:
Related to: