kumarhiranya/vrrec repository overview

⁠Room2XR

This repository contains a Docker image implementing the 3D reconstruction module for Room2XR: Virtual Interactive Collaboration in Real-world Scenes. It requires an NVIDIA GPU with at least 8GB VRAM to run. The setup and execution are facilitated using Docker and Conda.

⁠Prerequisites

Before setting up the project, ensure that you have the following installed on your system:

• Docker
• NVIDIA Docker Toolkit

⁠Setup

⁠1. Install Docker

• Follow the instructions on the Docker website⁠ to install Docker for your operating system.

⁠2. Install NVIDIA Docker Toolkit

• Follow the instructions on the NVIDIA Container Toolkit website⁠ to install the NVIDIA Docker Toolkit.

⁠Pull Docker Image

Pull docker image using:

docker pull kumarhiranya/vrrec:latest

⁠Running the Docker Container

Run the Docker container with GPU support:

docker run --gpus all -it kumarhiranya/vrrec:latest

Once inside the container, activate the vrrec Conda environment and start main.py while giving the IP address and Port (optional, defaults to 8052) from Leader's HoloLens 2 as input arguments:

conda activate cider
python main.py --ip ip_address --port 8052

Replace ip_address in the above command with the IP address from the Leader's HoloLens 2. IP address can be obtained by using the voice command "What is my IP address?" on HoloLens 2.