Dev

Endoscopy — 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
fiber_coupling -6.0 – 9.0 %
core_spacing -0.6 – 0.9 μm
bending_loss -0.36 – 0.54 dB

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinEndo + gradient 0.786 32.78 0.951 0.89 ✓ Certified Li et al., IEEE TMI 2023
2 TransEndo + gradient 0.774 32.61 0.949 0.84 ✓ Certified Wang et al., Med. Image Anal. 2022
3 PhysEndo + gradient 0.755 31.73 0.94 0.81 ✓ Certified Chen et al., Med. Image Anal. 2024
4 DiffEndo + gradient 0.749 30.13 0.919 0.9 ✓ Certified Gao et al., MICCAI 2024
5 EndoSLAM-Net + gradient 0.662 26.08 0.834 0.84 ✓ Certified Ozyoruk et al., Med. Image Anal. 2021
6 BM3D-Endo + gradient 0.649 24.99 0.802 0.89 ✓ Certified Dabov et al., IEEE TIP 2007
7 DnCNN-Endo + gradient 0.642 25.4 0.815 0.81 ✓ Certified Zhang et al., IEEE TIP 2017
8 CLAHE-Endo + gradient 0.597 23.42 0.747 0.82 ✓ Certified Zuiderveld, Graphics Gems IV 1994
9 Histogram-Eq + gradient 0.568 22.16 0.697 0.84 ✓ Certified Gonzalez & Woods, Digital Image Processing 2002

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 Endoscopy