# Syn3DTxt: Embedding 3D Cues for Scene Text Generation

arXiv: https://arxiv.org/abs/2505.18479 · HTML: https://mlsanity.com/paper/2505.18479/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 24 May 2025.

## Builds on (most cited first, 14 of 14)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [AnyText: Multilingual Visual Text Generation And Editing](https://mlsanity.com/paper/2311.03054/) (2023)
- [TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering](https://mlsanity.com/paper/2311.16465/) (2023)
- [Reading Text in the Wild with Convolutional Neural Networks](https://mlsanity.com/paper/1412.1842/) (2014)
- [Editing Text in the Wild](https://mlsanity.com/paper/1908.03047/) (2019)
- [TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control](https://mlsanity.com/paper/2410.10133/) (2024)
- [SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models](https://mlsanity.com/paper/2107.09313/) (2021)
- [Exploring Stroke-Level Modifications for Scene Text Editing](https://mlsanity.com/paper/2212.01982/) (2022)
- [GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation](https://mlsanity.com/paper/2303.17870/) (2023)
- [ICDAR 2023 Competition on Hierarchical Text Detection and Recognition](https://mlsanity.com/paper/2305.09750/) (2023)
- [First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blending](https://mlsanity.com/paper/2410.10168/) (2024)
- [SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds](https://mlsanity.com/paper/1907.06007/) (2019)

## Abstract (arXiv)

This study aims to investigate the challenge of insufficient three-dimensional context in synthetic datasets for scene text rendering. Although recent advances in diffusion models and related techniques have improved certain aspects of scene text generation, most existing approaches continue to rely on 2D data, sourcing authentic training examples from movie posters and book covers, which limits their ability to capture the complex interactions among spatial layout and visual effects in real-world scenes. In particular, traditional 2D datasets do not provide the necessary geometric cues for accurately embedding text into diverse backgrounds. To address this limitation, we propose a novel standard for constructing synthetic datasets that incorporates surface normals to enrich three-dimensional scene characteristic. By adding surface normals to conventional 2D data, our approach aims to enhance the representation of spatial relationships and provide a more robust foundation for future scene text rendering methods. Extensive experiments demonstrate that datasets built under this new standard offer improved geometric context, facilitating further advancements in text rendering under complex 3D-spatial conditions.