Nikolai10/MRIC
TensorFlow implementation of MRIC (Multi-Realism Image Compression with a Conditional Generator, CVPR 2023)
This tool helps researchers and content creators compress images efficiently while maintaining control over how realistic or accurate the reconstructed image appears. You input a high-quality image, and it outputs a highly compressed version that can be reconstructed to balance detail and fidelity. It's ideal for anyone needing to manage large volumes of images where file size and visual quality are critical, such as in scientific imaging or media archives.
No commits in the last 6 months.
Use this if you need to compress images significantly but also require flexibility in reconstructing them to either closely match the original or synthesize more visually appealing details, especially for low-bandwidth scenarios.
Not ideal if your primary concern is pixel-perfect, lossless compression where any synthesized detail is unacceptable.
Stars
31
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Nikolai10/MRIC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)