# JIA-Lab-research/SNR-Aware-Low-Light-Enhance

This is the official implementation for the paper "SNR-aware low-light image enhancement" in CVPR2022

Repository: https://github.com/JIA-Lab-research/SNR-Aware-Low-Light-Enhance
Canonical: https://ross.abutalabs.com/products/snr-aware-low-light-enhance
Language: Python
License Family: other
Last push: 2022-11-21T06:45:49+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1628, "days_push": 1381, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1037, forks 108 (observed 2026-08-28T04:03:19.500071+00:00)

## What it is
Official PyTorch implementation of the CVPR 2022 paper 'SNR-aware Low-Light Image Enhancement'. It combines SNR-aware transformers and convolutional models to enhance low-light images with spatial-varying operations guided by a signal-to-noise-ratio prior.

## Use cases
- enhance dark low-light photos
- brighten images taken in low light
- denoise and enhance low-SNR image regions
- train a low-light enhancement model on the LOL dataset
- reproduce CVPR 2022 low-light enhancement results
- evaluate low-light enhancement on SID, SMID, and SDSD datasets

## When to choose
- you need state-of-the-art low-light image enhancement with SNR-aware modeling
- you want a research-grade PyTorch codebase for the CVPR 2022 paper
- you are benchmarking on LOL, SID, SMID, or SDSD low-light datasets

## When to avoid
- you need a production-ready image enhancement service with support and license guarantees
- you want a simple one-line API without GPU or dataset setup
- you need enhancement of non-photographic or synthetic graphics

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, deep-learning, machine-learning
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python, windows
- tags: low-light-enhancement, snr-aware, cvpr2022, pytorch, image-restoration, research-code, transformers, linux, macos, gpu

## Member repositories
- JIA-Lab-research/SNR-Aware-Low-Light-Enhance (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.500071+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 2026-08-30T07:04:20.054357+00:00, confidence not recorded.
  - readme: https://github.com/JIA-Lab-research/SNR-Aware-Low-Light-Enhance (fetched 2026-08-28T04:03:19.500071+00:00, sha bb553b68ec68)
- Data as of 2026-08-30T08:39:29.467469+00:00.