# DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization

arXiv: https://arxiv.org/abs/2312.03568 · HTML: https://mlsanity.com/paper/2312.03568/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 6 Dec 2023.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [Focal Self-attention for Local-Global Interactions in Vision Transformers](https://mlsanity.com/paper/2107.00641/) (2021)
- [SelfDoc: Self-Supervised Document Representation Learning](https://mlsanity.com/paper/2106.03331/) (2021)
- [Multimodal Fusion Transformer for Remote Sensing Image Classification](https://mlsanity.com/paper/2203.16952/) (2022)
- [DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement](https://mlsanity.com/paper/2010.08764/) (2020)
- [DocDiff: Document Enhancement via Residual Diffusion Models](https://mlsanity.com/paper/2305.03892/) (2023)
- [DocEnTr: An End-to-End Document Image Enhancement Transformer](https://mlsanity.com/paper/2201.10252/) (2022)
- [Document Image Binarization with Fully Convolutional Neural Networks](https://mlsanity.com/paper/1708.03276/) (2017)
- [A selectional auto-encoder approach for document image binarization](https://mlsanity.com/paper/1706.10241/) (2017)
- [Polyp-SAM++: Can A Text Guided SAM Perform Better for Polyp Segmentation?](https://mlsanity.com/paper/2308.06623/) (2023)
- [SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization](https://mlsanity.com/paper/2105.05521/) (2021)

## Built on by (most cited first, 4 of 4)

- [Visual Text Processing: A Comprehensive Review and Unified Evaluation](https://mlsanity.com/paper/2504.21682/) (2025)
- [Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion](https://mlsanity.com/paper/2508.04055/) (2025)
- [DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarization](https://mlsanity.com/paper/2606.08781/) (2026)
- [DR-Mamba: Automatic Inference-Time Domain Adaptation for Document Image Binarization via Sample-Conditioned Detail-Background Suppression](https://mlsanity.com/paper/2606.22625/) (2026)

## Abstract (arXiv)

In real life, various degradation scenarios exist that might damage document images, making it harder to recognize and analyze them, thus binarization is a fundamental and crucial step for achieving the most optimal performance in any document analysis task. We propose DocBinFormer (Document Binarization Transformer), a novel two-level vision transformer (TL-ViT) architecture based on vision transformers for effective document image binarization. The presented architecture employs a two-level transformer encoder to effectively capture both global and local feature representation from the input images. These complimentary bi-level features are exploited for efficient document image binarization, resulting in improved results for system-generated as well as handwritten document images in a comprehensive approach. With the absence of convolutional layers, the transformer encoder uses the pixel patches and sub-patches along with their positional information to operate directly on them, while the decoder generates a clean (binarized) output image from the latent representation of the patches. Instead of using a simple vision transformer block to extract information from the image patches, the proposed architecture uses two transformer blocks for greater coverage of the extracted feature space on a global and local scale. The encoded feature representation is used by the decoder block to generate the corresponding binarized output. Extensive experiments on a variety of DIBCO and H-DIBCO benchmarks show that the proposed model outperforms state-of-the-art techniques on four metrics. The source code will be made available at https://github.com/RisabBiswas/DocBinFormer.