tue-mps/eomt

[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

56
/ 100
Established

This project offers a fast and straightforward way to analyze images and videos for segmentation tasks. It takes raw image or video files as input and outputs precise outlines and classifications for objects and regions within them. This tool is ideal for researchers, computer vision engineers, and data scientists working on tasks like medical imaging analysis, autonomous driving, or environmental monitoring.

548 stars. Actively maintained with 1 commit in the last 30 days.

Use this if you need to quickly and accurately identify and separate different objects or regions within images or video footage, especially if you're working with large pre-trained Vision Transformers.

Not ideal if your primary goal is object detection (bounding boxes) without needing detailed pixel-level segmentation, or if you prefer models with complex, task-specific decoders.

image-segmentation video-analysis computer-vision pattern-recognition medical-imaging
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

548

Forks

53

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 25, 2026

Commits (30d)

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tue-mps/eomt"

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