Research map / Architectures and efficiency / RNNs and normalization
DeepWave: A Recurrent Neural-Network for Real-Time Acoustic Imaging
Matthieu SIMEONI, Sepand Kashani, Paul Hurley, Martin Vetterli
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 |
|---|---|---|---|
| replace DAS imager with DeepWave | acoustic imaging · Dataset 1 (RW) | mean contrast: 0.89 (±0.07) -> 0.99 (±0.0081) | Improved |
| replace DAS imager with DeepWave | acoustic imaging · Dataset 1 (RW) snapshot | resolution (degrees): 25.3 -> 18.5 | Improved |
| replace DAS imager with DeepWave | acoustic imaging · Dataset 1 (RW) snapshot | RMS contrast: 0.78 -> 0.97 | Improved |
| replace DAS imager with DeepWave | acoustic imaging · Dataset 1 (RW) | resolution: approximately 27% | Improved |
| replace APGD iterative solver with DeepWave | acoustic imaging · runtime | runtime (ms): 211 ms -> 6.5 ms | Improved |
| replace DAS with DeepWave | acoustic imaging · runtime | runtime (ms): 2.0 ms -> 6.5 ms | Hurt |
| use physically-inspired initialisation instead of random initialisation (ablation) | DeepWave · training | training speed and performance | Improved |
| increase network depth beyond 5 or 6 layers (ablation) | DeepWave · Dataset 3 (SIM) | reconstruction quality | No clear effect |
Closest papers by meaning
- Point Clouds Meets Physics: Dynamic Acoustic Field Fitting Network for Point Cloud Understanding (CVPR 2025 · similarity 0.85)
- Deep Neural Room Acoustics Primitive (ICML 2024 · similarity 0.83)
- Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark (CVPR 2024 · similarity 0.83)
- RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction (ICLR 2025 · similarity 0.83)
- ResFields: Residual Neural Fields for Spatiotemporal Signals (ICLR 2024 · similarity 0.82)
- DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis (NeurIPS 2025 · similarity 0.82)
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.
