microsoft / microsoft/MoGe

MogeV2 ROS2 Node

Open
#116 0 comments 5 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
JavaScript
Stars
3k
Forks
234
PR merge metrics
No merged PRs in 30d

Description

https://github.com/user-attachments/assets/c03a8c50-b197-43a0-9ccf-41ebafa33e10

Hi guys,

for everyone interested deploying MoGeV2 in a robot, I have setup a ROS2 TensoRT inference node for MogeV2:

https://github.com/ika-rwth-aachen/ros2-moge-trt

I also provide a docker images, so the node is ready to deploy in your robot!

I am able to run MogeV2 in real time with following performance on a Nvidia RTX 6000:

  • VITS: 37 FPS
  • VITB: 31 FPS
  • VITL: 17 FPS

Best,
Till

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the linked external repository, ros2-moge-trt, and its Docker images to understand the proposed ROS2 TensorRT integration. The issue names no MoGe repository files, tests, or acceptance criteria, so the intended change and definition of done would need to be established before work begins.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker
Domain
computer-vision, robotics
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.