agneet42/robustness_depth_lang

[CVPR 2024] "On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation"

33
/ 100
Emerging

This project helps computer vision researchers understand how well language guidance works for tasks like monocular depth estimation. It takes an image and optional textual descriptions as input, then evaluates how robustly and accurately the system estimates the depth information for the scene. Computer vision scientists and engineers working on 3D scene understanding and perception systems would use this to evaluate the effectiveness of language-guided models.

No commits in the last 6 months.

Use this if you are a computer vision researcher evaluating the reliability and generalization capabilities of language-guided depth estimation models under various conditions.

Not ideal if you are looking for a plug-and-play solution for improving depth estimation in real-world applications without delving into research methodology and robustness analysis.

computer-vision depth-estimation language-guidance model-robustness 3D-scene-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Aug 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/agneet42/robustness_depth_lang"

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