ShuweiShao/NDDepth

[ICCV2023 Oral & TPAMI2024] NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion

37
/ 100
Emerging

NDDepth helps create detailed 3D representations of scenes from single 2D images. It takes a regular photo or video frame as input and outputs a depth map, which shows the distance of every point in the scene, and can also complete missing depth information. This is ideal for robotics engineers, autonomous vehicle developers, or augmented reality creators who need to understand the 3D structure of environments.

133 stars. No commits in the last 6 months.

Use this if you need highly accurate depth information from standard camera images for applications like robot navigation or 3D scene reconstruction.

Not ideal if you already have access to specialized 3D sensors or if your primary need is not highly precise 3D understanding from a single image.

robotics autonomous-driving 3D-reconstruction computer-vision augmented-reality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

133

Forks

10

Language

Python

License

MIT

Last pushed

Dec 30, 2024

Commits (30d)

0

Get this data via API

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

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