Justin-Tan/high-fidelity-generative-compression
A PyTorch implementation of the HIFIC neural image compression system that compresses images while preserving perceptual quality using learned representations.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of the High-Fidelity Generative Image Compression paper, using a learned compression model to reduce image file sizes by up to two orders of magnitude while maintaining visually similar reconstructions. It also includes a partial port of the TensorFlow Compression library, offering utilities for entropy coding and neural image compression in PyTorch.
Frequently asked
- What is Justin-Tan/high-fidelity-generative-compression?
- A PyTorch implementation of the HIFIC neural image compression system that compresses images while preserving perceptual quality using learned representations.
- Is high-fidelity-generative-compression open source?
- Yes — Justin-Tan/high-fidelity-generative-compression is open source, released under the Apache-2.0 license.
- What language is high-fidelity-generative-compression written in?
- Justin-Tan/high-fidelity-generative-compression is primarily written in Python.
- How popular is high-fidelity-generative-compression?
- Justin-Tan/high-fidelity-generative-compression has 478 stars on GitHub.
- Where can I find high-fidelity-generative-compression?
- Justin-Tan/high-fidelity-generative-compression is on GitHub at https://github.com/Justin-Tan/high-fidelity-generative-compression.