aayushbansal/PixelNet

The repository contains source code and models to use PixelNet architecture used for various pixel-level tasks. More details can be accessed at .

48
/ 100
Emerging

This project offers an architecture for pixel-level prediction problems, improving the efficiency and accuracy of tasks like image segmentation and object detection. It takes in raw image data and outputs detailed pixel-level classifications or estimations, such as identifying object boundaries or surface normals. Researchers and engineers working in computer vision or image processing would find this useful for developing advanced image analysis applications.

197 stars. No commits in the last 6 months.

Use this if you are a computer vision researcher or practitioner looking to train highly accurate models for detailed pixel-level tasks like semantic segmentation or surface normal estimation, even with limited data.

Not ideal if you need a plug-and-play solution for general image classification or object detection without delving into the underlying model architecture and training process.

image-segmentation computer-vision image-processing edge-detection surface-normal-estimation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

197

Forks

48

Language

Matlab

License

MIT

Last pushed

Jun 08, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aayushbansal/PixelNet"

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