fabiotosi92/Diffusion4RobustDepth

[ECCV 2024] Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions

28
/ 100
Experimental

This project helps self-driving car engineers and robotics developers enhance the accuracy of monocular depth estimation in challenging real-world scenarios. It takes existing images with clear depth information and transforms them into diverse, difficult conditions like rain, snow, low light, or reflective surfaces. The output is a robust depth estimation model capable of accurately perceiving depth even in adverse conditions.

No commits in the last 6 months.

Use this if you need to train or fine-tune monocular depth estimation models that perform reliably in adverse weather, low-light, or complex environments with reflective objects.

Not ideal if your application primarily involves ideal, well-lit, and clear visual conditions, as the focus here is on overcoming challenging data.

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

How are scores calculated?

Stars

93

Forks

1

Language

License

MIT

Last pushed

Sep 28, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/fabiotosi92/Diffusion4RobustDepth"

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