(CVPR2025) Learned Image Compression with Dictionary-based Entropy Model

Deep Contextual Video Compression

[TCSVT] RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion

[ICML 2025] Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-Aware Diffusion

Quick scripts to calculate CLIP text-image similarity

Official Implementation of "Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity (ICML 2024)"

[TCSVT 2025] Toward Extreme Image Compression with Latent Feature Guidance and Diffusion Prior

Code for Text + Sketch: Image Compression at Ultra Low Rates

[ICLR 2025] Pytorch implementation of the paper "Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation".

Lossy Compression with Pretrained Diffusion Models

Vector (and Scalar) Quantization, in Pytorch

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

Official Implementation for (ICLR 2024) Idempotence and Perceptual Image Compression

Official implementation of "Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model" (WACV2024).

A PyTorch library and evaluation platform for end-to-end compression research

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Entropy coding / arithmetic coding for PyTorch

A collection of tools for neural compression enthusiasts.

PyTorch re-implementation of Transformer-based Transform Coding

Data compression in TensorFlow

Implementation of Swin Transformers in TensorFlow along with converted pre-trained models, code for off-the-shelf classification and fine-tuning.

DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.

PyTorch implementation of Superpixel Sampling Networks

Clear implementation of arithmetic coding for educational purposes in Java, Python, C++.

Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).

Latex code for making neural networks diagrams

Compute receptive fields of your favorite convnets

ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation (CVPR20)