AMD ROCm Performance Primitives (RPP) library is a comprehensive high-performance computer vision library for AMD processors with HIP/OpenCL/CPU back-ends.

[ICRA 2025 Best Paper] MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry

Connect AI models like Claude & GPT with robots using MCP and ROS.

[ICCV 2023 & ICLR 2026] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

Python bindings for retinify

Official repository for LiteTracker: Leveraging Temporal Causality for Accurate Low-latency Tissue Tracking; published at MICCAI 2025.

Real-Time AI Stereo Vision Library

This is a summary of robot skills learning and the computer vision involved, including papers and code!

The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

Simple visualization tool

Standard Open Arm 100

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

[CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.

gradslam is an open source differentiable dense SLAM library for PyTorch

[IROS 2024] Representing 3D sparse map points and lines for camera relocalization; [IROS 2025] Improved 3D Point-Line Mapping Regression for Camera Relocalization

A generative world for general-purpose robotics & embodied AI learning.

A curated list of awesome Deep Stereo Matching resources

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

CoTracker is a model for tracking any point (pixel) on a video.

Deep Learning for Camera Calibration and Beyond: A Survey

GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

A Survey of Embodied Learning for Object-Centric Robotic Manipulation

Open3D: A Modern Library for 3D Data Processing

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Algorithms and Publications on 3D Object Tracking

Demo for "Real-time RGBD-based Extended Body Pose Estimation" paper

[CVPR 2024] Real-Time Open-Vocabulary Object Detection