# caoscott/SReC

PyTorch Implementation of "Lossless Image Compression through Super-Resolution"

Repository: https://github.com/caoscott/SReC
Canonical: https://ross.abutalabs.com/products/srec
Language: Python
License: MIT
License Family: permissive
Topics: lossless, compression, neural-network, pytorch
Last push: 2023-10-03T21:19:49+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2360, "days_push": 1065, "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 1051, forks 92 (observed 2026-08-28T04:03:23.128339+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: compression, image-processing, machine-learning, deep-learning
- domain: image-processing, machine-learning, computer-vision
- platform: python, cross-platform
- tags: lossless-compression, super-resolution, pytorch, research-code, neural-compression, gpu, linux

## Member repositories
- caoscott/SReC (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:23.128339+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 2026-08-30T07:00:02.737708+00:00, confidence not recorded.
  - readme: https://github.com/caoscott/SReC (fetched 2026-08-28T04:03:23.128339+00:00, sha b5a4ad5dd63b)
- Data as of 2026-08-30T08:39:29.467469+00:00.