The toolkit to test, validate, and evaluate your models and surface, curate, and prioritize the most valuable data for labeling.

Using deep learning models for image classification directly on the HoloLens 2.

Official code and data for EgoBody dataset (2022 ECCV)

CVPR2020. HOnnotate: A method for 3D Annotation of Hand and Object Poses

Google Research

UX tools and components for developing Mixed Reality applications in UE4.

Unity Plugin for using research mode functionality in HoloLens 2. Modified based on HoloLens2ForCV.

Sample Unity projects to demo how to use OpenXR plugin in Unity for HoloLens 2 and Mixed Reality headsets

Python scripts to download Assembly101 from Google Drive

Code samples that demonstrate how to use Microsoft's Platform for Situated Intelligence

Sample code and documentation for using the Microsoft HoloLens 2 for Computer Vision research.

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

visualization code for 3D human body annotation by EFT (Exemplar Fine-tuning)

2019 KAIST 딥러닝 홀로서기 세미나용 저장소입니다.

A cross platform (Linux and Windows) user mode SDK to read data from your Azure Kinect device.

Embed Python in Unreal Engine 4

Implementation of the model used in the paper Protest Activity Detection and Perceived Violence Estimation from Social Media Images (ACM Multimedia 2017)