Dev

Three-Photon Microscopy — Dev Tier

(5 scenes)

Blind evaluation tier — no ground truth available.

Measurements (y), ideal forward operator (H), and spec ranges only.

Apply your pipeline from the Public tier. Use consistency as self-check.

Reconstructed signals and corrected spec. Scored server-side.

🔒

True spec hidden — estimate parameters from spec ranges below.

Parameter	Spec Range	Unit
scattering_coeff	9.0 – 24.0	mm^-1
excitation_wavelength_shift	-2.4 – 3.6	nm
depth_dependent_psf	-0.48 – 0.72	-

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	DeconvFormer + gradient	0.778	33.21	0.954	0.82	✓ Certified	Chen et al., CVPR 2024
2	ScoreMicro + gradient	0.769	32.37	0.947	0.83	✓ Certified	Wei et al., ECCV 2025
3	Restormer+ + gradient	0.741	29.64	0.911	0.9	✓ Certified	Zamir et al., ICCV 2024
4	ResUNet + gradient	0.732	29.2	0.904	0.89	✓ Certified	DeCelle et al., Nat. Methods 2021
5	DiffDeconv + gradient	0.724	29.79	0.914	0.8	✓ Certified	Huang et al., NeurIPS 2024
6	Restormer + gradient	0.724	29.84	0.914	0.8	✓ Certified	Zamir et al., CVPR 2022
7	CARE + gradient	0.719	28.95	0.899	0.85	✓ Certified	Weigert et al., Nat. Methods 2018
8	U-Net + gradient	0.709	28.38	0.889	0.85	✓ Certified	Ronneberger et al., MICCAI 2015
9	TV-Deconvolution + gradient	0.665	25.74	0.825	0.89	✓ Certified	Rudin et al., Phys. A 1992
10	Wiener Filter + gradient	0.646	24.88	0.798	0.89	✓ Certified	Analytical baseline
11	PnP-DnCNN + gradient	0.628	24.35	0.781	0.86	✓ Certified	Zhang et al., IEEE TIP 2017
12	Richardson-Lucy + gradient	0.594	22.76	0.722	0.89	✓ Certified	Richardson, JOSA 1972 / Lucy, AJ 1974
13	PnP-FISTA + gradient	0.594	23.61	0.754	0.78	✓ Certified	Bai et al., 2020

y H_ideal spec_ranges

Format: HDF5

Scenes: 5

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

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