Dev

Fluoroscopy — Dev Tier

(3 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
motion_blur -6.0 – 9.0 ms
lag -3.6 – 5.4 ms
gain_drift -0.6 – 0.9 %

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PhysFluoro + gradient 0.782 33.2 0.954 0.84 ✓ Certified Chen et al., IEEE TMI 2024
2 TransFluoro + gradient 0.764 31.68 0.939 0.86 ✓ Certified Wang et al., IEEE TMI 2022
3 DiffFluoro + gradient 0.757 30.79 0.928 0.89 ✓ Certified Gao et al., MICCAI 2024
4 SwinFluoro + gradient 0.733 30.17 0.919 0.82 ✓ Certified Li et al., Med. Phys. 2023
5 REDCNN-Fluoro + gradient 0.684 26.65 0.849 0.89 ✓ Certified Chen et al., IEEE TMI 2017
6 DnCNN-Fluoro + gradient 0.657 26.02 0.833 0.82 ✓ Certified Chen et al., IEEE TMI 2017
7 NLM-Fluoro + gradient 0.649 25.45 0.816 0.84 ✓ Certified Buades et al., CVPR 2005
8 BM3D-Fluoro + gradient 0.572 22.61 0.715 0.8 ✓ Certified Dabov et al., IEEE TIP 2007
9 TV-Fluoro + gradient 0.489 19.1 0.555 0.88 ✓ Certified Sidky & Pan, Phys. Med. Biol. 2008

Visible Data Fields

y H_ideal spec_ranges

Dataset

Format: HDF5
Scenes: 3

Scoring Formula

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

PSNR: 40% SSIM: 40% Consistency: 20%
Back to Fluoroscopy