Research map / Probabilistic and scientific modeling / Dynamical systems
NeuralDMD: Interpretable Untrained Neural Network for Imaging from Sparse and Noisy Observations
Ali SaraerToosi, Renbo Tu, Esther Lin, Kamyar Azizzadenesheli, Aviad Levis
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 |
|---|---|---|---|
| parameterize Omega and b via small networks instead of direct optimization (ablation) | NeuralDMD · EHT 2017 Sgr A* | PSNR: 18.0 -> 29.18 | Improved |
| use NeuralDMD dynamic prior instead of vanilla MLP INR | INR baseline · EHT 2017 Sgr A* | PSNR: 26.0 -> 29.18 | Improved |
| raise positional-encoding bandwidth to L=10 (ablation) | NeuralDMD · EHT 2017 Sgr A* | PSNR: 29.18 -> 24.0 | Hurt |
| raise positional-encoding bandwidth to L=10 (ablation) | Vanilla MLP · EHT 2017 Sgr A* | PSNR: 26.0 -> 17.0 | Hurt |
| use NeuralDMD instead of SIREN/vanilla MLP for weather assimilation (~500 samples) | INR baselines · ERA5 weather | RMSE: 2.7 -> 2.3 | Improved |
| fit per instance instead of simulation-trained CORAL (OOD) | CORAL · 2D wave equation OOD | PSNR: 30±0.3 -> 43±1 | Improved |
| fit per instance instead of simulation-trained CORAL (ID) | CORAL · 2D wave equation ID | PSNR: 39±1 -> 56±1.3 | Improved |
| apply NeuralDMD to nonlinear flow (Re=5200 vs 200) and forecast | NeuralDMD · Navier-Stokes cylinder flow | PSNR: fit PSNR ~60 (Re=200) vs ~40 (Re=5200) | Hurt |
Closest papers by meaning
- Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction (NeurIPS 2026 · similarity 0.83)
- Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks (ICLR 2024 · similarity 0.83)
- AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data (ICLR 2025 · similarity 0.83)
- SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures (ICML 2025 · similarity 0.82)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.82)
- Gated Inference Network: Inference and Learning State-Space Models (NeurIPS 2024 · similarity 0.81)
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.
