This repository contains scripts to calculate the famous Bjontegaard-Delta metric with different interpolation functions.
-
Updated
Jul 3, 2024 - Python
#
rate-distortion
Here are 10 public repositories matching this topic...
Matlab code to compute entropy, conditional entropy, mutual information, channel capacity, and rate distortion.
-
Updated
Jun 29, 2020 - MATLAB
Reproducible research toolkit for benchmarking AVIF, JPEG XL, WebP, and JPEG on web images with perceptual quality metrics, statistical analysis, visual comparisons, and interactive reports.
python benchmarking web-performance reproducible-research jpeg plotly webp data-analysis matplotlib image-compression image-quality rate-distortion github-actions avif jpeg-xl perceptual-metrics interactive-report
-
Updated
Jul 6, 2026 - Python
Neural Distributed Compressor Discovers Binning [JSAIT 2024]
-
Updated
Jun 14, 2024 - Jupyter Notebook
Implementations of different ways to calculate Shannon's rate-distortion trade-off
-
Updated
May 28, 2020 - Jupyter Notebook
Projection as Conditional Expectation and the Capacity Ceiling (Cosmochrony non-injective foundations)
rate-distortion conditional-expectation cosmic-variance non-injective-projection low-multipole-anomaly distinguishable-histories contractive-projection averaging-operator
-
Updated
Jul 6, 2026 - TeX
Compute useful internal structure (C_u) for thermodynamic intelligence. Exact IB-optimal toy + neural network validation.
machine-learning intelligence entropy physics information-theory thermodynamics neural-networks complexity mutual-information non-equilibrium information-bottleneck rate-distortion adaptive-systems semantic-information landauer-principle
-
Updated
Apr 3, 2026 - Python
Code for signal recovery from quantized sparsified measurements with imperfect side information
-
Updated
Nov 2, 2017 - MATLAB
The honest head-to-head: silo (cluster to K intents, then transform) vs plain transformer (attend over N tokens). Untrained toys, so no fake accuracy -- the elbow method (variance explained) + rate-distortion (attention N^2->K^2 saved vs fidelity lost). Plain = K=N, agreement 1.0 by construction. A trade-off, not a winner. CC-BY-ND-4.0
-
Updated
Jul 8, 2026 - HTML
Rate-distortion metrics and theoretical bounds for neural speech tokenizers and discrete codebooks
-
Updated
Jun 29, 2026 - Python
Improve this page
Add a description, image, and links to the rate-distortion topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the rate-distortion topic, visit your repo's landing page and select "manage topics."