NVIDIA-ISAAC-ROS / NVIDIA-ISAAC-ROS/isaac_ros_pose_estimation

Is FoundationPose not real-time on Jetson AGX ORIN 64G devkit?

Open
#60 0 comments 4 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
501
Forks
57
PR merge metrics
No merged PRs in 30d

Description

Based on this screenshot, is it safe to assume that FoundationPose is far from real-time on Jetson AGX ORIN 64G? Is the reported number based on converting pth weight to TensorRT model or is it simply running the docker on Jetson?

I am wondering if there is any room for improvement for FoundationPose on Jetson AGX RIN 64G to make it (near-)real time (15-30 FPS)?

Screenshot 2025-01-06 at 9 29 39 PM

Contributor guide

Open the contributing guide

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 with the screenshot and the reported FoundationPose timing on the Jetson AGX ORIN 64G devkit. Clarify whether the measurement uses converted TensorRT weights or only the Docker setup, then benchmark possible improvements against the requested 15–30 FPS target. Done means the measurement conditions and achievable performance are documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, docker
Domain
computer-vision, embedded-iot, machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.