Dev

SAR — 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
motion_error -2.4 – 3.6 cm
phase_error -0.36 – 0.54 rad
range_cell_migration -0.6 – 0.9 cells

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffusionSAR + gradient 0.729 29.75 0.913 0.83 ✓ Certified Wei et al., NeurIPS 2024
2 SAR-CAM + gradient 0.704 28.2 0.885 0.84 ✓ Certified Cross-attention SAR, 2024
3 SARFormer + gradient 0.690 26.85 0.854 0.9 ✓ Certified Li et al., CVPR 2024
4 PanSharpener++ + gradient 0.654 25.7 0.823 0.84 ✓ Certified Zhang et al., ICCV 2024
5 ScoreSAR + gradient 0.627 24.14 0.773 0.88 ✓ Certified Johnson et al., ECCV 2025
6 Lee Filter + gradient 0.626 24.87 0.798 0.79 ✓ Certified Lee, IEEE TGRS 1980
7 SAR-DRN + gradient 0.617 24.23 0.777 0.82 ✓ Certified Zhang et al., RS 2018
8 Range-Doppler + gradient 0.613 23.97 0.767 0.83 ✓ Certified SAR signal processing baseline
9 SARDenoiserViT + gradient 0.606 24.03 0.77 0.79 ✓ Certified Wang et al., ICCV 2024
10 SAR-ResNet + gradient 0.572 22.08 0.693 0.87 ✓ Certified Chen et al., IEEE TGRS 2022
11 SAR-BM3D + gradient 0.555 21.54 0.67 0.86 ✓ Certified Parrilli et al., IEEE TGRS 2012
12 Matched Filter + gradient 0.499 19.98 0.598 0.8 ✓ Certified Standard SAR focusing
13 Chirp Scaling + gradient 0.495 19.98 0.598 0.78 ✓ Certified Raney et al., IEEE TGRS 1994

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%
Back to SAR