spatial-computing

A Python command-line utility for converting and processing 3D Gaussian Splatting models. Supports N-to-N conversion between 3DGS (.ply), KSplat, SOG, SPZ, Splat, CloudCompare, Parquet, and Compressed PLY. Includes GPU-accelerated filtering (SOR, Density).

Visual Asset Management System (VAMS) is a purpose-built, AWS native solution for the management and distribution of traditional to specialized visual assets used in physical AI and spatial computing.

A quaternion-driven traversal framework for trees and orientation-based data structures.

A Spatial Retrieval-Augmented Generation system for latent world models, designed for embodied spatial intelligence in robotics, autonomous navigation, and embodied AI. Features ROS2 integration, real-time inference @ 25Hz, and complete robot build guide.

Test-Time Memory Framework: Control Hallucinations in Foundation Models

Spatial display app for RayNeo Air AR glasses — pin your screen in 3D space with head tracking, add virtual monitors, create a multi-screen workspace through AR glasses

oneshotcopilot

Persistent agents. Spatial presence.

Open-source engine for spatial object placement from a single image

BIM Cloud Pipeline - full-stack Revit/IFC to GLB/GLTF + structured metadata JSON conversion service (FastAPI + Three.js). Built with NebulaCloud Studio.

Smaller, faster, less accurate VR hand-frame codec. The float16+zlib comparator still wins on fidelity (gate 0/5). ContactPose evaluation lane; PyPI v0.3.1.

Text to AR/VR: An end-to-end spatial AI pipeline that transforms unstructured textual descriptions of numerical data into immersive, interactive AR/VR visualizations using LLMs, a custom RAG framework and Unity.

SPL虚拟世界核心引擎：面向AI驱动的无叙事游戏世界与数字文明的开源底层操作系统，规则不可篡改，提供独立自洽的运行时内核，支持大规模虚拟生态、数字孪生、元宇宙、沙盒游戏、社会模拟等场景。

Autonomous AI vision agent with contextual memory for real-time spatial computing | Multi-modal LLM reasoning + YOLO grounding + persistent AR overlays | Next-gen hands-free AI interface

Local iPhone LiDAR-to-CAD pipeline that processes measurable digital-twin assets offline on Windows using open formats.

Spatial computing platform — hand-tracking turns empty air into a touchscreen (Phase-1 FastAPI backend prototype)

Open, cited and machine-readable database of AI glasses, smart glasses, display glasses and translation glasses. JSON/CSV/JSON-LD, CC BY 4.0. Unknown values are null, not estimated.

AI-first principles, knowledge graph, and evaluator for fast, accessible spatial computing in the browser.

Asynchronous spatial computing pipelines, kinetic telemetry engines, and real-time physics suites. Hyper-optimized for zero-latency 60+ FPS execution by decoupling deep learning tensor inferences (OpenCV, MediaPipe, YOLO) from parent execution loops.

GNOME display controls for VITURE XR glasses