ViTAE-Transformer/ViTAE-Transformer-Scene-Text-Detection

A comprehensive list [Hi-SAM@TPAMI'24, GoMatching@NeurIPS'24, DeepSolo(++)@ CVPR'23, DPText-DETR@AAAI'23, I3CL@IJCV'22] of our research works related to scene text detection, spotting, etc., including papers, codes.

25
/ 100
Experimental

This project offers tools to precisely identify and extract text from images and videos, including complex scenarios like curved or multilingual text and hierarchical structures (strokes, words, lines, paragraphs). It takes an image or video as input and outputs the detected text, often with bounding box or segmentation masks. This is for researchers and developers working on advanced computer vision applications involving optical character recognition (OCR) in real-world environments.

No commits in the last 6 months.

Use this if you need to perform highly accurate scene text detection, spotting, or hierarchical text segmentation from various image and video sources, especially when dealing with challenging text forms.

Not ideal if you're looking for a simple, off-the-shelf OCR solution for document scanning or basic text extraction from clean images, as this focuses on complex scene text research.

scene-text-detection video-text-spotting hierarchical-text-segmentation optical-character-recognition computer-vision-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

93

Forks

5

Language

TeX

License

Last pushed

Nov 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ViTAE-Transformer/ViTAE-Transformer-Scene-Text-Detection"

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