# Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis

arXiv: https://arxiv.org/abs/2511.12658 · HTML: https://mlsanity.com/paper/2511.12658/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 47 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Builds on (most cited first, 18 of 18)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2103.10596/) (2021)
- [TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization](https://mlsanity.com/paper/2212.10957/) (2022)
- [Image Manipulation Detection by Multi-View Multi-Scale Supervision](https://mlsanity.com/paper/2104.06832/) (2021)
- [Editing Text in the Wild](https://mlsanity.com/paper/1908.03047/) (2019)
- [AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics](https://mlsanity.com/paper/2304.06870/) (2023)
- [PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering](https://mlsanity.com/paper/2504.06632/) (2025)
- [Spatial Dual-Modality Graph Reasoning for Key Information Extraction](https://mlsanity.com/paper/2103.14470/) (2021)
- [AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation](https://mlsanity.com/paper/2308.01095/) (2023)
- [Document Rectification and Illumination Correction using a Patch-based CNN](https://mlsanity.com/paper/1909.09470/) (2019)
- [A large-scale dataset for end-to-end table recognition in the wild](https://mlsanity.com/paper/2303.14884/) (2023)
- [Revisiting Tampered Scene Text Detection in the Era of Generative AI](https://mlsanity.com/paper/2407.21422/) (2024)
- [CoVA: Context-aware Visual Attention for Webpage Information Extraction](https://mlsanity.com/paper/2110.12320/) (2021)
- [ReLoc: A Restoration-Assisted Framework for Robust Image Tampering Localization](https://mlsanity.com/paper/2211.03930/) (2022)
- [Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization](https://mlsanity.com/paper/2504.05224/) (2025)
- [OCR Graph Features for Manipulation Detection in Documents](https://mlsanity.com/paper/2009.05158/) (2020)

## Built on by (most cited first, 3 of 3)

- [DOCFORGE-BENCH: A Comprehensive 0-shot Benchmark for Document Forgery Detection and Analysis](https://mlsanity.com/paper/2603.01433/) (2026)
- [From Sharp Eyes to Expert Mind: Internalizing Expert Knowledge in MLLMs for Tampered Text Detection](https://mlsanity.com/paper/2609.36145/) (2026)
- [Agentic Tool-Augmented Reasoning for Explainable Image Forgery Detection](https://mlsanity.com/paper/2609.39066/) (2026)

## Abstract (arXiv)

Existing Text Image Forgery Localization (T-IFL) methods often suffer from poor generalization due to the limited scale of real-world datasets and the distribution gap caused by synthetic data that fails to capture the complexity of real-world tampering. To tackle this issue, we propose Fourier Series-based Tampering Synthesis (FSTS), a structured and interpretable framework for synthesizing tampered text images. FSTS first collects 16,750 real-world tampering instances from five representative tampering types, using a structured pipeline that records human-performed editing traces via multi-format logs (e.g., video, PSD, and editing logs). By analyzing these collected parameters and identifying recurring behavioral patterns at both individual and population levels, we formulate a hierarchical modeling framework. Specifically, each individual tampering parameter is represented as a compact combination of basis operation-parameter configurations, while the population-level distribution is constructed by aggregating these behaviors. Since this formulation draws inspiration from the Fourier series, it enables an interpretable approximation using basis functions and their learned weights. By sampling from this modeled distribution, FSTS synthesizes diverse and realistic training data that better reflect real-world forgery traces. Extensive experiments across four evaluation protocols demonstrate that models trained with FSTS data achieve significantly improved generalization on real-world datasets. Dataset is available at hrefhttps://github.com/ZeqinYu/FSTSProject Page.