Research map / Probabilistic and scientific modeling / Molecules and proteins
Cardio-mmFlow: A Gaussian-Prior-Free Physics-Informed Flow Matching Framework for Electrocardiogram to mmWave Radar Synthesis
Ziyang LIU, Ruiqiang Xiao, Chang Huang, KIEREN YU, Siyuan HE, Kaishun Wu
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 |
|---|---|---|---|
| initialize flow from ECG latent instead of Gaussian noise (ablation) | Cardio-mmFlow · ablation validation set | Latent-FID: 24.55 -> 14.98 | Improved |
| use MSD-FiLM instead of vanilla MLP-FiLM for metadata modulation (ablation) | Cardio-mmFlow · ablation validation set | Latent-FID: 18.273 -> 14.98 | Improved |
| use MSD-FiLM instead of AdaLN + crossAttn conditioning (ablation) | Cardio-mmFlow · ablation validation set | Latent-FID: 24.93 -> 14.98 | Improved |
| use MSD-FiLM instead of AdaLN + crossAttn conditioning (ablation) | Cardio-mmFlow · ablation validation set | MSE: 0.026 -> 0.027 | No clear effect |
| add spectral fidelity loss Lfreq (ablation) | Cardio-mmFlow · ablation validation set | PSD similarity: 0.819 -> 0.919 | Improved |
| add Wasserstein alignment loss LWD (ablation) | Cardio-mmFlow · ablation validation set | Latent-FID: 24.64 -> 14.98 | Improved |
| add classifier-free guidance (ablation) | Cardio-mmFlow · ablation validation set | Latent-FID: 18.11 -> 14.98 | Improved |
| add classifier-free guidance (ablation) | Cardio-mmFlow · ablation validation set | MSE: 0.029 -> 0.027 | No clear effect |
| train downstream AirECG on Cardio-mmFlow synthetic data instead of other generators' data | AirECG zero-shot mmWave-to-ECG · zero-shot, self-collected dataset | PCC: 0.74 -> 0.79 | Improved |
| add 10-40% real target-user calibration data to zero-shot model | AirECG · few-shot calibration | PCC: +4.17% at 10%; +2.95% at 40% | Improved |
| add 10-20% real calibration data | AirECG · few-shot calibration | RR error: +1.71% at 10%; +0.52% at 20% | No clear effect |
| use Cardio-mmFlow over PPGflowECG for heart-rate fidelity | synthesis · radar synthesis test | HR-AE (bpm): 6.00 -> 6.66 | Hurt |
Closest papers by meaning
- Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation (NeurIPS 2026 · similarity 0.84)
- Region-Disentangled Diffusion Model for High-Fidelity PPG-to-ECG Translation (AAAI 2024 · similarity 0.82)
- PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation (NeurIPS 2025 · similarity 0.81)
- Parallel-Learning of Invariant and Tempo-variant Attributes of Single-Lead Cardiac Signals: PLITA (AAAI 2025 · similarity 0.81)
- EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function (NeurIPS 2026 · similarity 0.81)
- Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals (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.
