# TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing

arXiv: https://arxiv.org/abs/2511.13399 · HTML: https://mlsanity.com/paper/2511.13399/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [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)
- [GlyphControl: Glyph Conditional Control for Visual Text Generation](https://mlsanity.com/paper/2305.18259/) (2023)
- [Editing Text in the Wild](https://mlsanity.com/paper/1908.03047/) (2019)
- [Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering](https://mlsanity.com/paper/2403.09622/) (2024)
- [SwapText: Image Based Texts Transfer in Scenes](https://mlsanity.com/paper/2003.08152/) (2020)
- [FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning](https://mlsanity.com/paper/2312.12142/) (2023)
- [Improving Diffusion Models for Scene Text Editing with Dual Encoders](https://mlsanity.com/paper/2304.05568/) (2023)
- [DiffUTE: Universal Text Editing Diffusion Model](https://mlsanity.com/paper/2305.10825/) (2023)
- [TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control](https://mlsanity.com/paper/2410.10133/) (2024)
- [Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model](https://mlsanity.com/paper/2312.12232/) (2023)
- [Exploring Stroke-Level Modifications for Scene Text Editing](https://mlsanity.com/paper/2212.01982/) (2022)
- [Visual Text Generation in the Wild](https://mlsanity.com/paper/2407.14138/) (2024)
- [Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing](https://mlsanity.com/paper/2405.04377/) (2024)
- [Deep Learning-based Forgery Attack on Document Images](https://mlsanity.com/paper/2102.00653/) (2021)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)

## Abstract (arXiv)

Scene Text Editing (STE) aims to naturally modify text in images while preserving visual consistency, the decisive factors of which can be divided into three parts, i.e., text style, text content, and background. Previous methods have struggled with incomplete disentanglement of editable attributes, typically addressing only one aspect - such as editing text content - thus limiting controllability and visual consistency. To overcome these limitations, we propose TripleFDS, a novel framework for STE with disentangled modular attributes, and an accompanying dataset called SCB Synthesis. SCB Synthesis provides robust training data for triple feature disentanglement by utilizing the "SCB Group", a novel construct that combines three attributes per image to generate diverse, disentangled training groups. Leveraging this construct as a basic training unit, TripleFDS first disentangles triple features, ensuring semantic accuracy through inter-group contrastive regularization and reducing redundancy through intra-sample multi-feature orthogonality. In the synthesis phase, TripleFDS performs feature remapping to prevent "shortcut" phenomena during reconstruction and mitigate potential feature leakage. Trained on 125,000 SCB Groups, TripleFDS achieves state-of-the-art image fidelity (SSIM of 44.54) and text accuracy (ACC of 93.58%) on the mainstream STE benchmarks. Besides superior performance, the more flexible editing of TripleFDS supports new operations such as style replacement and background transfer. Code: https://github.com/yusenbao01/TripleFDS