SonoWorld: From One Image to a 3D Audio-Visual Scene
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914431970050048 |
|---|---|
| author | Jin, Derong Chen, Xiyi Lin, Ming C. Gao, Ruohan |
| author_facet | Jin, Derong Chen, Xiyi Lin, Ming C. Gao, Ruohan |
| contents | Tremendous progress in visual scene generation now turns a single image into an explorable 3D world, yet immersion remains incomplete without sound. We introduce Image2AVScene, the task of generating a 3D audio-visual scene from a single image, and present SonoWorld, the first framework to tackle this challenge. From one image, our pipeline outpaints a 360° panorama, lifts it into a navigable 3D scene, places language-guided sound anchors, and renders ambisonics for point, areal, and ambient sources, yielding spatial audio aligned with scene geometry and semantics. Quantitative evaluations on a newly curated real-world dataset and a controlled user study confirm the effectiveness of our approach. Beyond free-viewpoint audio-visual rendering, we also demonstrate applications to one-shot acoustic learning and audio-visual spatial source separation. Project website: https://humathe.github.io/sonoworld/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28757 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SonoWorld: From One Image to a 3D Audio-Visual Scene Jin, Derong Chen, Xiyi Lin, Ming C. Gao, Ruohan Computer Vision and Pattern Recognition Multimedia Sound Tremendous progress in visual scene generation now turns a single image into an explorable 3D world, yet immersion remains incomplete without sound. We introduce Image2AVScene, the task of generating a 3D audio-visual scene from a single image, and present SonoWorld, the first framework to tackle this challenge. From one image, our pipeline outpaints a 360° panorama, lifts it into a navigable 3D scene, places language-guided sound anchors, and renders ambisonics for point, areal, and ambient sources, yielding spatial audio aligned with scene geometry and semantics. Quantitative evaluations on a newly curated real-world dataset and a controlled user study confirm the effectiveness of our approach. Beyond free-viewpoint audio-visual rendering, we also demonstrate applications to one-shot acoustic learning and audio-visual spatial source separation. Project website: https://humathe.github.io/sonoworld/ |
| title | SonoWorld: From One Image to a 3D Audio-Visual Scene |
| topic | Computer Vision and Pattern Recognition Multimedia Sound |
| url | https://arxiv.org/abs/2603.28757 |