Research map / Vision-language and multimodal / Cross-modal learning
Few-Shot Audio-Visual Learning of Environment Acoustics
Sagnik Majumder, Changan Chen, Ziad Al-Halah, Kristen Grauman
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 Few-ShotRIR instead of Fast-RIR++ | RIR prediction · Seen environments | STFT error: 1.37 -> 1.10 | Improved |
| Use Few-ShotRIR instead of Fast-RIR++ | RIR prediction · Unseen environments | MOSE: 15.2 -> 10.5 | Improved |
| Use Few-ShotRIR instead of Fast-RIR++ | RIR prediction · Seen environments | RTE: 1.25 -> 0.43 | Improved |
| Use Few-ShotRIR instead of Fast-RIR++ | RIR prediction · Unseen environments | DRRE: 369 -> 164 | Improved |
| Use Few-ShotRIR instead of NAF | RIR prediction · Unseen environments | STFT error: 3.62 -> 1.22 | Improved |
| Add echo inputs (ablation) | Few-ShotRIR · Seen environments | STFT error: 1.63 -> 1.10 | Improved |
| Add echo inputs (ablation) | Few-ShotRIR · Unseen environments | STFT error: 1.67 -> 1.22 | Improved |
| Add vision inputs (ablation) | Few-ShotRIR · Seen environments | STFT error: 1.63 -> 1.10 | Improved |
| Add vision inputs (ablation) | Few-ShotRIR · Unseen environments | STFT error: 1.58 -> 1.22 | Improved |
| Add energy decay matching loss L_D (ablation) | Few-ShotRIR · Seen environments | RTE: 1.60 -> 0.43 | Improved |
| Add energy decay matching loss L_D (ablation) | Few-ShotRIR · Unseen environments | RTE: 2.11 -> 0.65 | Improved |
| Increase observation set from N=1 to N=20 (ablation) | Few-ShotRIR · Seen environments | STFT error: 1.69 -> 1.10 | Improved |
Closest papers by meaning
- Hearing Anywhere in Any Environment (CVPR 2025 · similarity 0.92)
- AV-RIR: Audio-Visual Room Impulse Response Estimation (CVPR 2024 · similarity 0.92)
- Hearing Anything Anywhere (CVPR 2024 · similarity 0.90)
- Deep Neural Room Acoustics Primitive (ICML 2024 · similarity 0.88)
- Acoustic Volume Rendering for Neural Impulse Response Fields (NeurIPS 2024 · similarity 0.88)
- NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields (ICLR 2025 · 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.
