Public

Confocal Live-Cell — Public Tier

(5 scenes)

Full-access development tier with all data visible.

Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.

Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.

Reconstructed signals (x_hat) and corrected spec as HDF5.

✓

True spec visible — use these exact values for Scenario III oracle reconstruction.

Parameter	Spec Range	True Value	Unit
pinhole	-5.0 – 10.0	2.5	μm
refractive_index	1.51 – 1.525	1.5175
photobleaching	-5.0 – 10.0	2.5	%

Method: CPU_baseline — Mismatch parameter: nominal

13.27 dB

SSIM 0.3991

11.88 dB

SSIM 0.2385

19.75 dB

SSIM 0.4579

Per-scene breakdown (4 scenes)

Scene	PSNR I	SSIM I	PSNR II	SSIM II	PSNR III	SSIM III
scene_00	17.02	0.3838	14.94	0.2440	20.04	0.5013
scene_01	14.23	0.2969	12.92	0.2098	19.23	0.5480
scene_02	8.52	0.3871	8.01	0.2308	20.11	0.3417
scene_03	13.30	0.5284	11.66	0.2694	19.61	0.4408

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	DiffusionCell + gradient	0.857	37.54	0.98	0.95	✓ Certified	Gao et al., Nat. Methods 2024
2	Restormer-Micro + gradient	0.841	36.47	0.976	0.93	✓ Certified	Zamir et al., CVPR 2022 (microscopy)
3	SwinIR-LiveCell + gradient	0.824	35.19	0.969	0.92	✓ Certified	Liang et al., ICCV 2021 (live-cell)
4	PN2V + gradient	0.775	31.29	0.935	0.94	✓ Certified	Krull et al., ECCV 2020
5	CARE + gradient	0.759	30.62	0.926	0.91	✓ Certified	Weigert et al., Nat. Methods 2018
6	Noise2Void + gradient	0.738	29.81	0.914	0.87	✓ Certified	Krull et al., CVPR 2019
7	Noise2Self + gradient	0.707	27.61	0.872	0.91	✓ Certified	Batson & Royer, ICML 2019
8	NLM-Fluorescence + gradient	0.640	24.8	0.796	0.87	✓ Certified	Buades et al., CVPR 2005
9	VST-Denoise + gradient	0.603	22.71	0.72	0.94	✓ Certified	Anscombe, Biometrika 1948

y H_ideal spec_ranges x_true true_spec

Format: HDF5

Scenes: 5

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

PSNR: 40% SSIM: 40% Consistency: 20%