NVlabs/ParallelInversion

Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation (ICRA 2023)

34
/ 100
Emerging

This project helps robotics engineers and computer vision researchers precisely locate a camera in 3D space relative to an object or scene using just a single image. It takes an observed RGB image and a pre-trained Neural Radiance Field (NeRF) model of the target, then outputs the camera's exact 6-DoF position and orientation. This is useful for tasks requiring highly accurate camera pose estimation, especially in complex environments.

No commits in the last 6 months.

Use this if you need robust and efficient 6-DoF camera pose estimation from a single image for robotics or augmented reality applications, even in challenging conditions.

Not ideal if you only have traditional 2D images without a corresponding NeRF model of the scene, or if you need real-time performance on embedded systems without powerful GPUs.

robotics computer-vision camera-pose-estimation augmented-reality 3d-reconstruction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

35

Forks

4

Language

Cuda

License

Last pushed

Oct 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NVlabs/ParallelInversion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.