Intellindust-AI-Lab/EdgeCrafter

Pytorch implementation of "EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation"

42
/ 100
Emerging

This tool helps engineers and researchers accurately identify and locate objects or specific body parts within images or video streams, even on devices with limited computing power. You provide images as input, and it outputs precise bounding boxes around detected objects, segmented outlines, or keypoint estimations for pose tracking. It's designed for anyone deploying computer vision models in real-world scenarios on edge devices.

Use this if you need to perform real-time object detection, instance segmentation, or pose estimation on edge devices like embedded systems, drones, or smart cameras, where computational efficiency and accuracy are critical.

Not ideal if your primary need is large-scale cloud-based image analysis or if you require extremely high-precision models without any concern for processing speed or device memory limitations.

real-time object detection robotics vision edge AI human pose estimation industrial inspection
No Package No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 14 / 25

How are scores calculated?

Stars

15

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Mar 21, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Intellindust-AI-Lab/EdgeCrafter"

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