Research map / 3D vision / 3D generation
SonoWorld: From One Image to a 3D Audio-Visual Scene
Derong Jin, Xiyi Chen, Ming C. Lin, Ruohan Gao
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 proprietary models (Marble, GPT-5) instead of open-source (HunyuanWorld, LLaVA-Next-34B) | SonoWorld · SonoScene360 | angular error (lower better): 0.975 -> 0.728 | Improved |
| use proprietary models instead of open-source | SonoWorld · SonoScene360 | D-CLAP R-Precision: 52.9% -> 67.6% | Improved |
| replace visual-input spatial audio generators with grounded 3D ambisonics encoding | SonoWorld (open-source) · SonoScene360 | CC: 0.148 -> 0.491 | Improved |
| replace MMAudio with grounded spatial encoding | SonoWorld (open-source) · SonoScene360 | D-CLAP audio-text: 0.322 -> 0.413 | Improved |
| use differentiable renderer vs neural acoustic fields | SonoWorld · One-shot room acoustic learning | angular error: 1.58 -> 0.22 | Improved |
| use differentiable renderer vs neural acoustic fields | SonoWorld · One-shot room acoustic learning | MAG error: 3.96 -> 3.46 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AV-NeRF — AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis (NeurIPS 2023) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Audible World Models: Spatially Aware Sound Generation for 3D Worlds (NeurIPS 2026 · similarity 0.88)
- SoundBrush: Sound as a Brush for Visual Scene Editing (AAAI 2025 · similarity 0.88)
- NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields (ICLR 2025 · similarity 0.87)
- Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation (ICLR 2025 · similarity 0.87)
- OmniAudio: Generating Spatial Audio from 360-Degree Video (ICML 2025 · similarity 0.87)
- AV-Cloud: Spatial Audio Rendering Through Audio-Visual Cloud Splatting (NeurIPS 2024 · similarity 0.86)
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.
