Dev
Ultrasound — Dev Tier
(3 scenes)Blind evaluation tier — no ground truth available.
What you get
Measurements (y), ideal forward operator (H), and spec ranges only.
How to use
Apply your pipeline from the Public tier. Use consistency as self-check.
What to submit
Reconstructed signals and corrected spec. Scored server-side.
Parameter Specifications
🔒
True spec hidden — estimate parameters from spec ranges below.
| Parameter | Spec Range | Unit |
|---|---|---|
| sos | 1516.0 – 1576.0 | m/s |
| attenuation | 0.38 – 0.68 | dB/cm/MHz |
| element_sensitivity | -6.0 – 9.0 | % |
| phase_aberration | -0.36 – 0.54 | rad |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | BeamDATA + gradient | 0.733 | 29.91 | 0.915 | 0.84 | ✓ Certified | Smith et al., ICCV 2024 |
| 2 | AttentionBeam + gradient | 0.732 | 30.06 | 0.918 | 0.82 | ✓ Certified | Xu et al., ECCV 2024 |
| 3 | UltrasoundFormer + gradient | 0.721 | 29.76 | 0.913 | 0.79 | ✓ Certified | Park et al., CVPR 2024 |
| 4 | BeamFormer + gradient | 0.711 | 28.06 | 0.882 | 0.89 | ✓ Certified | Li et al., ICCV 2024 |
| 5 | Phase-ADMM-Net + gradient | 0.670 | 26.77 | 0.852 | 0.81 | ✓ Certified | Hou et al., IEEE TMI 2022 |
| 6 | ScoreUS + gradient | 0.662 | 25.68 | 0.823 | 0.88 | ✓ Certified | Johnson et al., ECCV 2025 |
| 7 | DiffUS + gradient | 0.634 | 25.12 | 0.806 | 0.8 | ✓ Certified | Chen et al., NeurIPS 2024 |
| 8 | PW-DAS + gradient | 0.608 | 23.88 | 0.764 | 0.82 | ✓ Certified | Plane wave synthesis baseline |
| 9 | ABLE + gradient | 0.600 | 23.44 | 0.748 | 0.83 | ✓ Certified | Luijten et al., IEEE TMI 2020 |
| 10 | MU-Net + gradient | 0.582 | 23.16 | 0.737 | 0.78 | ✓ Certified | Hyun et al., IEEE TUFFC 2022 |
| 11 | PnP-ADMM + gradient | 0.580 | 22.37 | 0.706 | 0.87 | ✓ Certified | Goudarzi et al., 2020 |
| 12 | DAS + gradient | 0.562 | 21.84 | 0.683 | 0.85 | ✓ Certified | Analytical baseline |
| 13 | DAS-CF + gradient | 0.560 | 22.31 | 0.703 | 0.78 | ✓ Certified | Capon filter, IEEE 1969 |
| 14 | PnP-TV + gradient | 0.492 | 19.27 | 0.563 | 0.87 | ✓ Certified | TV regularization for ultrasound |
Visible Data Fields
y
H_ideal
spec_ranges
Dataset
Format: HDF5
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%