duanyiqun/DiffusionDepth

PyTorch Implementation of introducing diffusion approach to 3D depth perception ECCV 2024

45
/ 100
Emerging

This project helps convert a standard 2D image into a depth map, which shows how far away objects are from the camera. You provide a single image, and it outputs a corresponding image where pixel brightness represents depth. This is useful for professionals in fields like autonomous driving or robotics who need to understand the 3D structure of a scene from 2D photos.

339 stars.

Use this if you need to precisely estimate the depth of every pixel in a scene using only a single photograph.

Not ideal if you already have multiple camera views or LiDAR data to determine depth, as this tool focuses on inferring depth from a single image.

3D-reconstruction autonomous-navigation robotics computer-vision scene-understanding
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

339

Forks

23

Language

Python

License

Apache-2.0

Last pushed

Oct 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/duanyiqun/DiffusionDepth"

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