StereoSync: Spatially-Aware Stereo Audio Generation from Video

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Marinoni, Christian, Gramaccioni, Riccardo Fosco, Shimada, Kazuki, Shibuya, Takashi, Mitsufuji, Yuki, Comminiello, Danilo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911195679686656
author Marinoni, Christian
Gramaccioni, Riccardo Fosco
Shimada, Kazuki
Shibuya, Takashi
Mitsufuji, Yuki
Comminiello, Danilo
author_facet Marinoni, Christian
Gramaccioni, Riccardo Fosco
Shimada, Kazuki
Shibuya, Takashi
Mitsufuji, Yuki
Comminiello, Danilo
contents Although audio generation has been widely studied over recent years, video-aligned audio generation still remains a relatively unexplored frontier. To address this gap, we introduce StereoSync, a novel and efficient model designed to generate audio that is both temporally synchronized with a reference video and spatially aligned with its visual context. Moreover, StereoSync also achieves efficiency by leveraging pretrained foundation models, reducing the need for extensive training while maintaining high-quality synthesis. Unlike existing methods that primarily focus on temporal synchronization, StereoSync introduces a significant advancement by incorporating spatial awareness into video-aligned audio generation. Indeed, given an input video, our approach extracts spatial cues from depth maps and bounding boxes, using them as cross-attention conditioning in a diffusion-based audio generation model. Such an approach allows StereoSync to go beyond simple synchronization, producing stereo audio that dynamically adapts to the spatial structure and movement of a video scene. We evaluate StereoSync on Walking The Maps, a curated dataset comprising videos from video games that feature animated characters walking through diverse environments. Experimental results demonstrate the ability of StereoSync to achieve both temporal and spatial alignment, advancing the state of the art in video-to-audio generation and resulting in a significantly more immersive and realistic audio experience.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05828
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StereoSync: Spatially-Aware Stereo Audio Generation from Video
Marinoni, Christian
Gramaccioni, Riccardo Fosco
Shimada, Kazuki
Shibuya, Takashi
Mitsufuji, Yuki
Comminiello, Danilo
Sound
Computer Vision and Pattern Recognition
Machine Learning
Multimedia
Audio and Speech Processing
Although audio generation has been widely studied over recent years, video-aligned audio generation still remains a relatively unexplored frontier. To address this gap, we introduce StereoSync, a novel and efficient model designed to generate audio that is both temporally synchronized with a reference video and spatially aligned with its visual context. Moreover, StereoSync also achieves efficiency by leveraging pretrained foundation models, reducing the need for extensive training while maintaining high-quality synthesis. Unlike existing methods that primarily focus on temporal synchronization, StereoSync introduces a significant advancement by incorporating spatial awareness into video-aligned audio generation. Indeed, given an input video, our approach extracts spatial cues from depth maps and bounding boxes, using them as cross-attention conditioning in a diffusion-based audio generation model. Such an approach allows StereoSync to go beyond simple synchronization, producing stereo audio that dynamically adapts to the spatial structure and movement of a video scene. We evaluate StereoSync on Walking The Maps, a curated dataset comprising videos from video games that feature animated characters walking through diverse environments. Experimental results demonstrate the ability of StereoSync to achieve both temporal and spatial alignment, advancing the state of the art in video-to-audio generation and resulting in a significantly more immersive and realistic audio experience.
title StereoSync: Spatially-Aware Stereo Audio Generation from Video
topic Sound
Computer Vision and Pattern Recognition
Machine Learning
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2510.05828