biswassanket/DocSegTr
A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers
This project helps researchers and academics automatically understand the structure of scientific papers. It takes an image of a document page and outputs a precise map of distinct content areas like text blocks, figures, and tables. This tool is designed for anyone needing to analyze or extract specific sections from academic documents.
No commits in the last 6 months.
Use this if you need to programmatically identify and separate different logical components within document images, such as for content extraction or layout analysis.
Not ideal if you are looking for a simple, off-the-shelf application or web tool without needing to engage in a technical setup.
Stars
59
Forks
8
Language
Python
License
GPL-3.0
Last pushed
Sep 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/biswassanket/DocSegTr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
qubvel-org/segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
tue-mps/eomt
[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
OSUPCVLab/SegFormer3D
Official Implementation of SegFormer3D: an Efficient Transformer for 3D Medical Image...
jeya-maria-jose/Medical-Transformer
Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image...
davidiommi/Pytorch--3D-Medical-Images-Segmentation--SALMON
Segmentation deep learning ALgorithm based on MONai toolbox: single and multi-label segmentation...