iwa-shi/CRDR
Official implementation of "Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model" (WACV2024).
This project offers a single tool for compressing images while precisely balancing file size, visual quality (distortion), and how lifelike the image appears. You provide an uncompressed image, and it outputs a smaller, compressed image where you can adjust these trade-offs. This is ideal for professionals like digital artists, photographers, or media specialists who need fine-grained control over image output for various platforms or storage needs.
No commits in the last 6 months.
Use this if you need advanced control over the balance between image file size, visual quality, and realism for your images.
Not ideal if you're looking for a simple, one-click image compression tool without needing to fine-tune quality parameters.
Stars
23
Forks
—
Language
Python
License
—
Category
Last pushed
Jun 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/iwa-shi/CRDR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TheMatrixMaster/edit-flows-demo
Educational Implementation of "Edit Flows: Flow Matching with Edit Operations" by Havasi et al.
tokkiwa/FlashGMM
Official repository for the paper “FlashGMM: Fast Gaussian Mixture Entropy Model for Learned...
beneboeck/sparse-bayesian-gen-mod
Source code of the Paper "Sparse Bayesian Generative Modeling for Compressive Sensing" (NeurIPS 24)