Dev

DOT — 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
mu_a -12.0 – 18.0 %
mu_s -9.6 – 14.4 %
source_pos -1.2 – 1.8 mm

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffusionDOT + gradient 0.788 33.47 0.957 0.85 ✓ Certified Gao et al., NeurIPS 2024
2 PhysDOT + gradient 0.739 29.65 0.911 0.89 ✓ Certified Chen et al., Opt. Express 2024
3 TransDOT + gradient 0.733 29.49 0.909 0.87 ✓ Certified Li et al., IEEE TMI 2022
4 SwinDOT + gradient 0.727 29.87 0.915 0.81 ✓ Certified Wang et al., Biomed. Opt. Express 2023
5 FEM-DOT + gradient 0.595 23.42 0.747 0.81 ✓ Certified Schweiger et al., J. Biomed. Opt. 2005
6 DOT-Net + gradient 0.517 20.68 0.631 0.79 ✓ Certified Guo et al., Biomed. Opt. Express 2021
7 DnCNN-DOT + gradient 0.498 19.76 0.587 0.83 ✓ Certified Yoo et al., Sci. Rep. 2019
8 Born-Approx + gradient 0.423 17.35 0.468 0.81 ✓ Certified Arridge, Inverse Probl. 1999
9 TV-DOT + gradient 0.358 14.99 0.354 0.83 ✓ Certified Borsic et al., IEEE TMI 2010

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 DOT