{"type":"ScholarlyArticle","title":"SpatialV2A: Visual-Guided High-fidelity Spatial Audio Generation","authors":[{"name":"Yanan Wang","slug":"yanan-wang","given":"Yanan","family":"Wang","affiliation":""},{"name":"Linjie Ren","slug":"linjie-ren","given":"Linjie","family":"Ren","affiliation":""},{"name":"Zihao Li","slug":"zihao-li","given":"Zihao","family":"Li","affiliation":""},{"name":"Junyi Wang","slug":"junyi-wang","given":"Junyi","family":"Wang","affiliation":""},{"name":"Tian Gan","slug":"tian-gan","given":"Tian","family":"Gan","affiliation":""}],"abstract":"While video-to-audio generation has achieved remarkable progress in semantic and temporal alignment, most existing studies focus solely on these aspects, paying limited attention to the spatial perception and immersive quality of the synthesized audio. This limitation stems largely from current models' reliance on mono audio datasets, which lack the binaural spatial information needed to learn visual-to-spatial audio mappings. To address this gap, we introduce two key contributions: we construct BinauralVGGSound, the first large-scale video-binaural audio dataset designed to support spatially aware video-to-audio generation; and we propose an end-to-end spatial audio generation framework guided by visual cues that explicitly models spatial features. Our framework incorporates a visual-guided audio spatialization module that ensures the generated audio exhibits realistic spatial attributes and layered spatial depth while maintaining semantic and temporal alignment. Experiments show that our approach substantially outperforms state-of-the-art models in spatial fidelity and delivers a more immersive auditory experience, without sacrificing temporal or semantic consistency. All datasets, code, and model checkpoints are available at: https://github.com/renlinjie868-web/SpatialV2A.","doi":"10.24963/ijcai.2026/198","url":"https://ijcai.org/proceedings/2026/198","pdf":"https://ijcai.org/proceedings/2026/0198.pdf","markdown":"https://ijcai.org/proceedings/2026/198.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/198","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":198,"pages":{"first":1776,"last":1784},"keywords":["Computer Vision: Image and video synthesis and generation","Computer Vision: Video analysis and understanding","Computer Vision: Multimodal learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}