GitGud-f/Delta

A Lightweight Deep Learning Model for Depth Estimation. Aimed to run on edge devices and provide near-real-time results. This project uses knowledge distillation technology to transfer knowledge from DepthAnythingV2 to a smaller model

23
/ 100
Experimental

This project helps you create a specialized computer vision model that can understand the 3D layout of a scene from a single 2D image, much like a human does. You input a regular photo, and it outputs a 'depth map' showing how far away objects are. It's designed for mobile apps or devices that need to quickly analyze images, making it useful for augmented reality, robotics, or any application requiring real-time spatial awareness.

No commits in the last 6 months.

Use this if you need to integrate fast, accurate depth perception from standard camera images into mobile applications or edge devices where computational resources are limited.

Not ideal if you require extremely precise, lidar-quality depth measurements for scientific or industrial applications where even minor inaccuracies are critical.

augmented-reality robotics mobile-vision 3d-reconstruction computer-vision
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

18

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/GitGud-f/Delta"

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