Research map / Video / Video segmentation and tracking
Self-Supervised Generation of Spatial Audio for 360° Video
Pedro Morgado, Nuno Nvasconcelos, Timothy Langlois, Oliver Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the task-tailored separation and localization architecture instead of a generic U-Net | 360° spatial audio generation · YT-Music | EMD: 2.855 -> 2.350 | Improved |
| Add visual RGB and flow features (ablation) | Ours-Full · YT-All | EMD: 2.117 -> 2.019 | Improved |
| Add the RGB visual encoder (ablation) | Ours-Full · YT-Music | EMD: 2.432 -> 2.350 | Improved |
| Add the flow visual encoder (ablation) | Ours-Full · YT-All | EMD: 2.023 -> 2.019 | Improved |
| Add the source separation block (ablation) | Ours-Full · YT-Music | EMD: 2.447 -> 2.350 | Improved |
| Use the learned model rather than a dataset-wide spatial prior | 360° spatial audio generation · YT-Music | EMD: 3.479 -> 2.350 | Improved |
| Use the full model instead of a U-Net baseline | 360° spatial audio generation · REC-Street | ENV: 0.935 -> 0.767 | Improved |
Closest papers by meaning
- OmniAudio: Generating Spatial Audio from 360-Degree Video (ICML 2025 · similarity 0.89)
- MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations (NeurIPS 2025 · similarity 0.88)
- Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation (ICLR 2025 · similarity 0.88)
- ViSAGe: Video-to-Spatial Audio Generation (ICLR 2025 · similarity 0.87)
- Supervising Sound Localization by In-the-wild Egomotion (CVPR 2025 · similarity 0.87)
- The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
