Professional Desktop Application for Converting Video Frames to 4D Gaussian Splatting Sequences using Apple's SHARP Model

A set of experiments using augmented reality. WebXR + Threejs are the predominate tools used.

World tracking for WebAR. A Javascript library for Augmented Reality to run SLAM in the browser.

Set up multiple RDP sessions easily - portable, UI-based, works offline, Windows updates-resistant.

One-click Portable Windows installation of 'AI-Toolkit by Ostris'

A real-time streaming video bot that generates talking avatar videos with ultra-low latency using: Piper TTS for lightning-fast, natural-sounding speech Wav2Lip for lip-sync animation Streaming arc…

a open framework for blind navigation based on esp32

A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).

Foundation Models and Data for Human-Human and Human-AI interactions.

MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025)

A Sample Project for Passthrough Camera API in Unity.

A Unity package that enables real-time computer vision operations on Meta Quest headsets using the Passthrough Camera API (PCA) with WebRTC streaming to external servers for AI inference.

[CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"

Open-Source Frontier Voice AI

Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

Generative Motion Latent Flow Matching for Audio-driven Talking Portrait

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

DeepVerse: 4D Autoregressive Video Generation as a World Model

Official implementation of our NeurIPS paper "Streaming Radiance Fields for 3D Video Synthesis"

Democratizing Augmented Reality research and development.

An open source SDK for logging, storing, querying, and visualizing multimodal and multi-rate data

📦Portable package for running Hunyuan3D 2.0/2.1 on Windows. | 混元 3D 2.0/2.1 整合包

Real time interactive streaming digital human

A developer-friendly platform for comparing language model performance, calculating API costs, and refining prompts across multiple providers (GPT-3.5, Gemini, and more). Features real-time token p…

3D Gaussian Splat Editor

Controlling Insta360 cameras via BLE using an ESP32

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.