Zongliang-Wu/LADE-DUN

[ECCV'24 - Best Paper Award Candidate & Oral] Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging.

34
/ 100
Emerging

This project helps scientists and researchers reconstruct detailed 3D spatial-spectral images from a single 2D compressed measurement. It takes a single-shot compressed spectral image as input and produces a high-quality, detailed 3D image that reveals spatial and spectral information. This is useful for anyone working with hyperspectral imaging and needing to recover rich data from limited input.

No commits in the last 6 months.

Use this if you need to reconstruct high-fidelity hyperspectral images from challenging, heavily compressed single-shot measurements.

Not ideal if your workflow doesn't involve snapshot spectral compressive imaging or if you are looking for a general-purpose image reconstruction tool.

hyperspectral imaging spectral reconstruction remote sensing biomedical imaging material science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

48

Forks

5

Language

Python

License

MIT

Last pushed

Mar 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Zongliang-Wu/LADE-DUN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.