caoscott/SReC

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1051 stars · 92 forks observed · 2026-08-28

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

SReC is the official PyTorch implementation of the paper 'Lossless Image Compression through Super-Resolution', which frames lossless image compression as a super-resolution problem solved with neural networks. It supports training, compression, and decompression, achieving state-of-the-art compression rates with practical runtimes.

Use cases

• compress images losslessly with neural networks
• reproduce results from the SReC paper
• train a learned lossless image compression model
• compress large image datasets at state-of-the-art bitrates
• experiment with super-resolution based compression

When to choose

• you need learned lossless image compression with pretrained weights
• you want to reproduce or extend published neural compression research
• you work in PyTorch and need training plus compression/decompression pipelines

When to avoid

• you need general-purpose file compression like zip or png for everyday use
• you lack a GPU or need fast real-time compression
• you need lossy compression or video compression
• you need production-supported software rather than research code

Facets

library · maturity maintenance

compression image-processing machine-learning deep-learning image-processing machine-learning computer-vision python cross-platform lossless-compression super-resolution pytorch research-code neural-compression gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="caoscott/SReC")