A 3D renderer and engine for Apple platforms. We strive to build a Swift and Metal–first foundation for real-time rendering and XR, designed for developers who want full control.

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

PyTorch implementation for Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything

This is the project of paper: Real-Time Instance Segmentation and Tip Detection for Surgical Instruments in Neuroendoscopic Surgery.

OpenMMLab Pose Estimation Toolbox and Benchmark.

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

A curated list of free, high-quality, university-level courses with video lectures related to the field of Computer Vision.

Implementation of neural stereo matching on the Apple Vision Pro with RAFT-Stereo

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

Optical Flow SDK exposes the latest hardware capability of Turing GPUs dedicated to computing the relative motion of pixels between images. The hardware uses sophisticated algorithms to yield highl…

The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".

An open access book on scientific visualization using python and matplotlib

A game theoretic approach to explain the output of any machine learning model.

Model Interpretation through Sensitivity Analysis for Segmentation

[CVPR 2025] DEFOM-Stereo: Depth foundation model based stereo matching

Render Gaussian Splats using Metal on Apple platforms (iOS/iPhone/iPad, macOS, and visionOS)

The KartaLink "Spatial Metadata" tools allow you to prepare immersive content for playback on Apple Vision Pro and Meta Quest HMDs

VisionOS App + Python Library to stream hand tracking data from Vision Pro, video/audio stream to Vision Pro.

List of resources for visionOS developers!

Group-wise Correlation Stereo Network, CVPR 2019

ARKit VIO/SLAM projects

Swift library for FHIR® resource data models

Streamlined, ergonomic APIs around Apple's Vision framework

Scripts for exporting YOLOv5 models to CoreML and benchmarking it.

Implementation of the photogeometric ICP algorithm in OpenCL