# DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis

arXiv: https://arxiv.org/abs/2107.02638 · HTML: https://mlsanity.com/paper/2107.02638/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 6 Jul 2021.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [Modulating early visual processing by language](https://mlsanity.com/paper/1707.00683/) (2017)
- [LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators](https://mlsanity.com/paper/1901.06767/) (2019)
- [GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images](https://mlsanity.com/paper/2003.02567/) (2020)
- [READ: Recursive Autoencoders for Document Layout Generation](https://mlsanity.com/paper/1909.00302/) (2019)

## Built on by (most cited first, 17 of 17)

- [DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition](https://mlsanity.com/paper/2203.12273/) (2022)
- [OCR-IDL: OCR Annotations for Industry Document Library Dataset](https://mlsanity.com/paper/2202.12985/) (2022)
- [Beyond Document Page Classification: Design, Datasets, and Challenges](https://mlsanity.com/paper/2308.12896/) (2023)
- [Rethinking Layered Graphic Design Generation with a Top-Down Approach](https://mlsanity.com/paper/2507.05601/) (2025)
- [SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation](https://mlsanity.com/paper/2305.00795/) (2023)
- [Synthetic Document Generator for Annotation-free Layout Recognition](https://mlsanity.com/paper/2111.06016/) (2021)
- [DocSynthv2: A Practical Autoregressive Modeling for Document Generation](https://mlsanity.com/paper/2406.08354/) (2024)
- [Graph-based Deep Generative Modelling for Document Layout Generation](https://mlsanity.com/paper/2107.04357/) (2021)
- [SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding](https://mlsanity.com/paper/2408.14764/) (2024)
- [Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence](https://mlsanity.com/paper/2601.12318/) (2026)
- [DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning](https://mlsanity.com/paper/2501.12898/) (2025)
- [A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts](https://mlsanity.com/paper/2209.10441/) (2022)
- [UnSupDLA: Towards Unsupervised Document Layout Analysis](https://mlsanity.com/paper/2406.06236/) (2024)
- [Relation-Rich Visual Document Generator for Visual Information Extraction](https://mlsanity.com/paper/2504.10659/) (2025)
- [MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning](https://mlsanity.com/paper/2505.20513/) (2025)
- [Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding](https://mlsanity.com/paper/2511.04699/) (2025)
- [Search-Based Risk Feature Discovery in Document Structure Spaces under a Constrained Budget](https://mlsanity.com/paper/2601.21608/) (2026)

## Abstract (arXiv)

Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to automatically synthesize document images based on a given layout. In this work, given a spatial layout (bounding boxes with object categories) as a reference by the user, our proposed DocSynth model learns to generate a set of realistic document images consistent with the defined layout. Also, this framework has been adapted to this work as a superior baseline model for creating synthetic document image datasets for augmenting real data during training for document layout analysis tasks. Different sets of learning objectives have been also used to improve the model performance. Quantitatively, we also compare the generated results of our model with real data using standard evaluation metrics. The results highlight that our model can successfully generate realistic and diverse document images with multiple objects. We also present a comprehensive qualitative analysis summary of the different scopes of synthetic image generation tasks. Lastly, to our knowledge this is the first work of its kind.