Li-Chongyi/Zero-DCE

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1067 stars · 229 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

PyTorch implementation of Zero-DCE (Zero-Reference Deep Curve Estimation), a CVPR 2020 model that enhances low-light images without paired or reference training data. It includes training/testing scripts, a pretrained snapshot, and a MindSpore variant.

Use cases

• brighten dark photos with a deep learning model
• low-light image enhancement without reference data
• reproduce Zero-DCE CVPR 2020 results
• train a zero-reference enhancement network
• enhance underexposed images in a research pipeline

When to choose

• you need research-grade low-light enhancement with a pretrained model
• you want a lightweight, zero-reference enhancement approach
• you're studying or extending CVPR 2020 enhancement methods

When to avoid

• you need a commercially licensed solution (code is CC BY-NC)
• you need production-maintained software with releases and support
• you need a general-purpose image editing toolkit

Facets

library · maturity maintenance

image-processing deep-learning machine-learning computer-vision image-processing deep-learning python low-light-enhancement zero-reference-learning cvpr-2020 pytorch research-code non-commercial-license gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Li-Chongyi/Zero-DCE")