Ghost alternatives for AI agents.

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Scenic: A Jax Library for Computer Vision Research and Beyond

A python library for self-supervised learning on images.

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Powerful & Easy-to-Use Video Face Swapping and Editing Software

An open source library and framework for deep learning on satellite and aerial imagery.

记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

Training library for local feature detection and matching

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

Accelerated deep learning R&D