multimedialabsfu/learned-compression-of-encoding-distributions
[ICIP 2024] Lightweight distribution compression for neural image compression
This project helps image compression researchers and engineers create more efficient neural image compression models. It takes neural network latent representations as input and outputs a more accurate, dynamically adapted encoding distribution. This allows for improved image compression by better matching the varied characteristics of different input images.
No commits in the last 6 months.
Use this if you are developing neural image compression algorithms and want to reduce the 'amortization gap' for better compression efficiency.
Not ideal if you are an end-user simply looking to compress images with existing tools, as this is a research-focused component for model development.
Stars
9
Forks
—
Language
Python
License
—
Category
Last pushed
Jun 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/multimedialabsfu/learned-compression-of-encoding-distributions"
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)