dsshim0125/SwinDepth

"SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Network" (ICRA 2023)

26
/ 100
Experimental

This project helps convert a sequence of standard camera images into detailed depth maps, showing how far away objects are from the camera. You provide a video sequence (or a folder of images), and it generates corresponding depth maps. This is useful for researchers and engineers working on autonomous vehicles, robotics, or 3D scene understanding.

No commits in the last 6 months.

Use this if you need to quickly estimate the depth of objects in a scene from monocular video footage without requiring specialized depth sensors.

Not ideal if you require real-time depth sensing for dynamic environments or need extremely high-precision depth measurements for industrial applications.

autonomous-vehicles robotics computer-vision 3d-scene-reconstruction depth-perception
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

39

Forks

1

Language

Python

License

MIT

Last pushed

Mar 08, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/dsshim0125/SwinDepth"

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