A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers
☆59Sep 9, 2024Updated last year
Alternatives and similar repositories for DocSegTr
Users that are interested in DocSegTr are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICDAR 2023] SelfDocSeg: A self-supervised vision-based approach towards Document Segmentation (Oral)☆42Oct 6, 2023Updated 2 years ago
- Scene Text Aware Cross Modal Retrieval (StacMR)☆24Sep 3, 2021Updated 4 years ago
- Optocal Character Recognition (OCR / HTR) using Transformers☆11Aug 20, 2022Updated 3 years ago
- CLIP-based simple image-text matching baseline for COCO and F30K☆14Sep 16, 2021Updated 4 years ago
- [WACV 2026 Round 1] Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout☆22Oct 11, 2025Updated 5 months ago
- DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022☆186Jan 17, 2025Updated last year
- Official PyTorch Implementation of DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis - ICDAR 2021☆92Jul 16, 2021Updated 4 years ago
- ICDAR 2019☆25Aug 2, 2019Updated 6 years ago
- Document Image Enhancement with GANs - TPAMI journal☆217Mar 24, 2023Updated 2 years ago
- STVQA and TextVQA OCR results from Amazon Text in Image pipeline☆12Jul 18, 2022Updated 3 years ago
- code for our BMVC 2021 paper "HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification"☆15Oct 28, 2022Updated 3 years ago
- The official repo of the Comics Survey: "A missing piece in Vision and Language: A Survey on Comics Understanding"☆134Jan 2, 2025Updated last year
- Official implementation of "Relational Proxies: Emergent Relationships as Fine-Grained Discriminators", NeurIPS 2022.☆14Feb 1, 2025Updated last year
- Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.☆137Oct 18, 2025Updated 5 months ago
- The official implement of CTRNet++.☆14Dec 30, 2024Updated last year
- Repository to use/train segmentation models for document layout analysis☆19Jan 13, 2022Updated 4 years ago
- Trained Detectron2 object detection models for document layout analysis based on PubLayNet dataset☆29Apr 16, 2023Updated 2 years ago
- Example codebase for fine-tuning layoutLMv3 on DocVQA☆53Sep 19, 2022Updated 3 years ago
- A curated list of resources on Table Structure Recognition☆34Jul 31, 2025Updated 7 months ago
- Project page for the ICDAR 2023 Paper "Inv3D: a high-resolution 3D invoice dataset for template-guided single-image document unwarping".☆13Dec 21, 2023Updated 2 years ago
- ECCV 2022: Abstracting Sketches through Simple Primitives☆27Jan 19, 2024Updated 2 years ago
- Using FCN to segment the book's content and background, then dewarping the pages,☆21Oct 9, 2021Updated 4 years ago
- The official code for “DeepEraser: Deep Iterative Context Mining for Generic Text Eraser”, TMM, 2024.☆48Aug 26, 2024Updated last year
- [TAI 2023] Appearance Enhancement for Camera-captured Document Images in the Wild☆52Aug 28, 2025Updated 6 months ago
- Document Layout Analysis☆402Mar 13, 2026Updated last week
- Multi-Headed Self-Attention via Vision Transformer for Zero-Shot Learning (ViT-ZSL)☆33Aug 3, 2021Updated 4 years ago
- Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement - AAAI 2023☆28Jul 12, 2023Updated 2 years ago
- ☆38Feb 4, 2023Updated 3 years ago
- Code for the ICDAR2021 paper "Visual FUDGE: Form Understanding via Dynamic Graph Editing"☆33Mar 4, 2022Updated 4 years ago
- Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task…☆288Feb 13, 2023Updated 3 years ago
- Doodle to Search: Practical Zero Shot Sketch Based Image Retrieval☆80Sep 30, 2022Updated 3 years ago
- DocILE: Document Information Localization and Extraction Benchmark☆142May 15, 2024Updated last year
- The official code for “Deep Unrestricted Document Image Rectification”, TMM, 2023.☆513Feb 1, 2026Updated last month
- Self-supervised learning of visual features through embedding images into text topic spaces☆94Aug 20, 2022Updated 3 years ago
- Code from our paper "Template-guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction " (ICCVW) 2023.☆28Feb 7, 2024Updated 2 years ago
- From document (PDF) or document images to analysis ready semi-structured data.☆20Nov 4, 2022Updated 3 years ago
- Unofficial implementation of DocMAE (WIP): Document Image Rectification via Self-supervised Representation Learning☆20Dec 20, 2023Updated 2 years ago
- A hobby project that dewarps book pages in images☆19Jan 5, 2023Updated 3 years ago
- Measure the diversity of image descriptions, repository for our COLING 2018 paper.☆13Dec 29, 2019Updated 6 years ago