ShuweiShao/MonoDiffusion

[TCSVT2024] MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model

32
/ 100
Emerging

This project helps convert standard 2D images into detailed 3D depth maps, without needing special equipment or pre-existing 3D data. It takes a single 2D image as input and outputs a corresponding depth map, showing the distance of objects from the camera. This is useful for researchers and engineers working on autonomous vehicles, robotics, or computer vision applications.

No commits in the last 6 months.

Use this if you need to understand the 3D structure of a scene from a single camera image, especially in applications where collecting precise 3D data is difficult or impossible.

Not ideal if you already have access to stereo cameras or LiDAR data, as this tool focuses on inferring depth from monocular (single-camera) input.

autonomous-driving robotics 3D-reconstruction computer-vision scene-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

32

Forks

3

Language

Python

License

MIT

Last pushed

Mar 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ShuweiShao/MonoDiffusion"

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