Hidden

Spectral CT — Hidden Tier

(3 scenes)

Fully blind server-side evaluation — no data download.

No data downloadable. Algorithm runs server-side on hidden measurements.

Package algorithm as Docker container / Python script. Submit via link.

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

🔒

True spec hidden — blind evaluation, only ranges available.

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	CT-ViT + gradient	0.735	30.38	0.922	0.81	✓ Certified	Guo et al., NeurIPS 2024
2	CTFormer + gradient	0.716	29.21	0.904	0.81	✓ Certified	Li et al., ICCV 2024
3	DiffusionCT + gradient	0.715	29.86	0.915	0.75	✓ Certified	Kazemi et al., ECCV 2024
4	PnP-DnCNN + gradient	0.704	28.88	0.898	0.78	✓ Certified	Zhang et al., IEEE TIP 2017
5	Score-CT + gradient	0.695	28.71	0.895	0.75	✓ Certified	Song et al., NeurIPS 2024
6	DuDoTrans + gradient	0.690	27.33	0.866	0.85	✓ Certified	Wang et al., MLMIR 2022
7	FBPConvNet + gradient	0.690	28.07	0.882	0.78	✓ Certified	Jin et al., IEEE TIP 2017
8	DOLCE + gradient	0.673	26.67	0.85	0.83	✓ Certified	Liu et al., ICCV 2023
9	TV-ADMM + gradient	0.671	27.4	0.868	0.75	✓ Certified	Sidky et al., Phys. Med. Biol. 2008
10	PnP-ADMM + gradient	0.668	26.82	0.854	0.79	✓ Certified	Venkatakrishnan et al., IEEE GlobalSIP 2013
11	Learned Primal-Dual + gradient	0.667	26.2	0.838	0.85	✓ Certified	Adler & Oktem, IEEE TMI 2018
12	RED-CNN + gradient	0.615	24.81	0.796	0.74	✓ Certified	Chen et al., IEEE TMI 2017
13	FBP + gradient	0.585	22.64	0.717	0.86	✓ Certified	Kak & Slaney, IEEE Press 1988

Scenes: 3

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

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