princeton-computational-imaging/HNDR

Official code repository for the paper: "The Implicit Values of A Good Hand Shake: Handheld Multi-Frame Neural Depth Refinement"

41
/ 100
Emerging

This project helps computer vision researchers refine depth perception in images captured with handheld cameras. By taking multiple slightly different images and their corresponding initial depth estimates and camera positions, it produces a more accurate, high-resolution 3D depth map. It's designed for researchers developing or evaluating advanced imaging techniques for applications like augmented reality or robotics.

No commits in the last 6 months.

Use this if you are a computer vision researcher needing to significantly improve the 3D depth accuracy of images captured with a moving handheld camera.

Not ideal if you need a real-time depth solution for live camera feeds or do not have access to initial depth estimates and camera pose data.

computer-vision 3d-reconstruction depth-estimation computational-photography multi-view-imaging
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

72

Forks

12

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/princeton-computational-imaging/HNDR"

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