# caiyuanhao1998/MST

A toolbox for spectral compressive imaging reconstruction including MST (CVPR 2022), CST (ECCV 2022), DAUHST (NeurIPS 2022), BiSCI (NeurIPS 2023), HDNet (CVPR 2022), MST++ (CVPRW 2022), etc.

Repository: https://github.com/caiyuanhao1998/MST
Canonical: https://ross.abutalabs.com/products/mst
Language: Python
License: MIT
License Family: permissive
Topics: image-restoration, hyperspectral-images, snapshot-compressive-imaging, spectral-reconstruction, binarized-neural-networks, bnn, qnn, transformer, ntire
Last push: 2025-10-10T21:58:06+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 46, release rhythm 35, longevity 100
- inputs: {"age_days": 1643, "days_push": 327, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1118, forks 89 (observed 2026-08-28T04:03:39.199082+00:00)

## What it is
A Python toolbox for spectral compressive imaging reconstruction that implements over 15 algorithms including MST, CST, DAUHST, BiSCI, HDNet, and MST++. It serves as a research baseline with pre-trained models, training logs, and evaluation for hyperspectral image reconstruction.

## Use cases
- reconstruct hyperspectral images from compressive measurements
- reproduce CVPR and NeurIPS spectral imaging papers
- benchmark spectral reconstruction algorithms
- recover spectral images from RGB
- train deep learning models for snapshot compressive imaging
- compare transformer-based image restoration methods

## When to choose
- you need state-of-the-art spectral compressive imaging baselines
- you want pre-trained models and training code for hyperspectral reconstruction
- you are doing research on snapshot compressive imaging or spectral recovery

## When to avoid
- you need a production-ready image processing pipeline rather than research code
- your task is general RGB image restoration unrelated to spectral imaging
- you need a GUI tool rather than a Python research codebase

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python
- tags: hyperspectral-imaging, snapshot-compressive-imaging, spectral-reconstruction, image-restoration, transformer, research-code, pytorch, benchmark, linux, gpu

## Member repositories
- caiyuanhao1998/MST (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:39.199082+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:41:27.848627+00:00, confidence not recorded.
  - readme: https://github.com/caiyuanhao1998/MST (fetched 2026-08-28T04:03:39.199082+00:00, sha fde283d05c4a)
- Data as of 2026-08-30T08:39:29.467469+00:00.