Public

Adaptive Optics (AO) Imaging — 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
dm_actuator_gain	0.98 – 1.04	1.01	-
wfs_centroid_bias	-0.04 – 0.08	0.02	px
fried_parameter_r0	0.13 – 0.19	0.16	m
servo_lag	-0.4 – 0.8	0.2	ms

Method: CPU_baseline — Mismatch parameter: nominal

7.77 dB

SSIM 0.3772

7.61 dB

SSIM 0.1940

15.93 dB

SSIM 0.4222

Per-scene breakdown (4 scenes)

Scene	PSNR I	SSIM I	PSNR II	SSIM II	PSNR III	SSIM III
scene_00	7.57	0.3615	7.48	0.1918	15.88	0.4337
scene_01	7.70	0.3833	7.85	0.1983	15.89	0.4210
scene_02	7.97	0.3846	7.45	0.1929	16.02	0.4175
scene_03	7.84	0.3794	7.67	0.1931	15.94	0.4166

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	DiffusionAO + gradient	0.805	33.44	0.956	0.94	✓ Certified	Score-based diffusion for wavefront reconstruction, 2024
2	AO-ViT + gradient	0.767	31.2	0.933	0.91	✓ Certified	Vision transformer for AO, 2024
3	AO-Transformer + gradient	0.751	30.14	0.919	0.91	✓ Certified	Wavefront sensing transformer, 2023
4	LIFT-Net + gradient	0.729	29.07	0.901	0.89	✓ Certified	Orban de Xivry et al., MNRAS 2021
5	WFNet + gradient	0.698	27.15	0.862	0.91	✓ Certified	Nishizaki et al., Opt. Express 2019
6	PnP-ADMM (WF) + gradient	0.640	24.61	0.79	0.89	✓ Certified	Venkatakrishnan et al., 2013
7	Fried Estimator + gradient	0.603	22.86	0.726	0.92	✓ Certified	Fried, JOSA 1977
8	Zernike LS + gradient	0.497	19.17	0.558	0.91	✓ Certified	Noll, JOSA 1976

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%