Dev

LiDAR — Dev Tier

(5 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
timing_jitter -60.0 – 90.0 ps
beam_divergence -0.12 – 0.18 mrad
range_walk -1.2 – 1.8 cm

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 Point Transformer + gradient 0.730 29.7 0.912 0.84 ✓ Certified Zhao et al., ICCV 2021
2 Bilateral Filter + gradient 0.628 24.69 0.792 0.82 ✓ Certified Tomasi & Manduchi, ICCV 1998
3 PnP-ADMM + gradient 0.605 23.41 0.747 0.86 ✓ Certified Venkatakrishnan et al., 2013
4 RandLA-Net + gradient 0.593 23.18 0.738 0.83 ✓ Certified Hu et al., CVPR 2020

Visible Data Fields

y H_ideal spec_ranges

Dataset

Format: HDF5
Scenes: 5

Scoring Formula

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

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