Dev

Polarimetric SAR (PolSAR) — 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
cross_talk_between_polarizations -9.0 – 6.0 dB
channel_imbalance -0.24 – 0.36 dB
faraday_rotation -1.2 – 1.8 deg

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SARFormer + gradient 0.742 29.8 0.914 0.89 ✓ Certified Li et al., CVPR 2024
2 DiffusionSAR + gradient 0.693 27.07 0.86 0.89 ✓ Certified Wei et al., NeurIPS 2024
3 SARDenoiserViT + gradient 0.688 27.53 0.871 0.82 ✓ Certified Wang et al., ICCV 2024
4 PanSharpener++ + gradient 0.677 26.59 0.848 0.86 ✓ Certified Zhang et al., ICCV 2024
5 SAR-CAM + gradient 0.656 25.39 0.814 0.88 ✓ Certified Cross-attention SAR, 2024
6 ScoreSAR + gradient 0.643 24.9 0.799 0.87 ✓ Certified Johnson et al., ECCV 2025
7 SAR-DRN + gradient 0.623 24.73 0.793 0.79 ✓ Certified Zhang et al., RS 2018
8 Range-Doppler + gradient 0.606 23.96 0.767 0.8 ✓ Certified SAR signal processing baseline
9 SAR-BM3D + gradient 0.605 23.49 0.75 0.85 ✓ Certified Parrilli et al., IEEE TGRS 2012
10 Chirp Scaling + gradient 0.593 23.17 0.738 0.83 ✓ Certified Raney et al., IEEE TGRS 1994
11 Lee Filter + gradient 0.560 22.21 0.699 0.79 ✓ Certified Lee, IEEE TGRS 1980
12 SAR-ResNet + gradient 0.541 21.38 0.663 0.81 ✓ Certified Chen et al., IEEE TGRS 2022
13 Matched Filter + gradient 0.493 19.72 0.585 0.81 ✓ Certified Standard SAR focusing

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 Polarimetric SAR (PolSAR)