amazon-science/glass-text-spotting
Official implementation for "GLASS: Global to Local Attention for Scene-Text Spotting" (ECCV'22)
This project helps automatically find and read text within complex images, even if the text is small, rotated, or blended into the background. It takes an image as input and outputs the detected text along with its location in the image. This tool is useful for anyone working with visual data that contains varying and challenging text elements.
102 stars. No commits in the last 6 months.
Use this if you need to accurately extract text from diverse real-world images where text size, orientation, and context vary significantly.
Not ideal if you primarily work with clean, high-contrast images where text is always horizontal and easily legible.
Stars
102
Forks
13
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/amazon-science/glass-text-spotting"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BR-IDL/PaddleViT
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
pathak22/unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
IBM/CrossViT
Official implementation of CrossViT. https://arxiv.org/abs/2103.14899
NVlabs/GCVit
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
ViTAE-Transformer/ViTDet
Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object...