Dev

Dark-Field Microscopy — Dev Tier

(5 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
condenser_na_vs_objective_na_ratio 1.128 – 1.308 -
stray_light -1.2 – 1.8 relative
scattering_angle_range -0.15 – 0.15 -

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 Restormer-DF + gradient 0.770 32.94 0.952 0.8 ✓ Certified Zamir et al., CVPR 2022 (DF)
2 DiffusionDF + gradient 0.760 32.24 0.945 0.8 ✓ Certified Luo et al., arXiv 2023 (DF)
3 SwinIR-DF + gradient 0.760 30.97 0.93 0.89 ✓ Certified Liang et al., ICCV 2021 (DF)
4 BM3D-DF + gradient 0.739 30.27 0.921 0.84 ✓ Certified Dabov et al., IEEE TIP 2007 (DF adapt.)
5 Noise2Void-DF + gradient 0.650 25.58 0.82 0.83 ✓ Certified Krull et al., CVPR 2019 (DF)
6 Wiener-DF + gradient 0.640 24.62 0.79 0.89 ✓ Certified Wiener, 1949 (DF adapt.)
7 CARE-DF + gradient 0.639 25.2 0.808 0.82 ✓ Certified Weigert et al., Nat. Methods 2018 (DF)
8 Richardson-Lucy + gradient 0.568 21.94 0.687 0.87 ✓ Certified Richardson, JOSA 1972; Lucy, AJ 1974
9 TV-DF + gradient 0.513 20.17 0.607 0.84 ✓ Certified Rudin et al., Physica D 1992 (DF)

Visible Data Fields

y H_ideal spec_ranges

Dataset

Format: HDF5
Scenes: 5

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to Dark-Field Microscopy