Dev

FPM — 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
led_position -0.12 – 0.18 mm
na_error 0.094 – 0.109
defocus -2.4 – 3.6 μm

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 Gradient Descent FPM + gradient 0.660 26.31 0.841 0.8 ✓ Certified Tian & Waller, Optica 2015
2 PtychoDV + gradient 0.653 26.11 0.835 0.79 ✓ Certified Shamshad et al., IEEE TCI 2019
3 Fourier PtychoNet + gradient 0.580 22.74 0.721 0.82 ✓ Certified Jiang et al., BOE 2018
4 Alternating Projections + gradient 0.568 22.16 0.697 0.84 ✓ Certified Zheng et al., Nat. Photonics 2013

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 FPM