# Edit Fidelity Field: Semantics-Aware Region Isolation for Training-Free Scene Text Editing

arXiv: https://arxiv.org/abs/2604.17500 · HTML: https://mlsanity.com/paper/2604.17500/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 19 Apr 2026.

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

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [AnyText2: Visual Text Generation and Editing With Customizable Attributes](https://mlsanity.com/paper/2411.15245/) (2024)
- [SwapText: Image Based Texts Transfer in Scenes](https://mlsanity.com/paper/2003.08152/) (2020)
- [STEFANN: Scene Text Editor using Font Adaptive Neural Network](https://mlsanity.com/paper/1903.01192/) (2019)
- [TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control](https://mlsanity.com/paper/2410.10133/) (2024)
- [FonTS: Text Rendering with Typography and Style Controls](https://mlsanity.com/paper/2412.00136/) (2024)
- [GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models](https://mlsanity.com/paper/2407.02252/) (2024)
- [DreamText: High Fidelity Scene Text Synthesis](https://mlsanity.com/paper/2405.14701/) (2024)
- [TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering](https://mlsanity.com/paper/2602.20903/) (2026)
- [Recognition-Synergistic Scene Text Editing](https://mlsanity.com/paper/2503.08387/) (2025)
- [GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing](https://mlsanity.com/paper/2505.04915/) (2025)
- [EditID: Training-Free Editable ID Customization for Text-to-Image Generation](https://mlsanity.com/paper/2503.12526/) (2025)
- [EditIDv2: Editable ID Customization with Data-Lubricated ID Feature Integration for Text-to-Image Generation](https://mlsanity.com/paper/2509.05659/) (2025)
- [Dual-Channel Attention Guidance for Training-Free Image Editing Control in Diffusion Transformers](https://mlsanity.com/paper/2602.18022/) (2026)
- [GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering](https://mlsanity.com/paper/2603.15616/) (2026)
- [TextMaster: A Unified Framework for Realistic Text Editing via Glyph-Style Dual-Control](https://mlsanity.com/paper/2410.09879/) (2024)
- [GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows](https://mlsanity.com/paper/2603.12155/) (2026)
- [FlexID: Training-Free Flexible Identity Injection via Intent-Aware Modulation for Text-to-Image Generation](https://mlsanity.com/paper/2602.07554/) (2026)
- [Edit Spillover as a Probe: Do Image Editing Models Implicitly Understand World Relations?](https://mlsanity.com/paper/2603.17876/) (2026)

## Abstract (arXiv)

Scene text editing (STE) has achieved remarkable progress in accurately rendering target text through diffusion-based methods. However, we identify a critical yet overlooked problem: edit spillover -- when editing a target text region, existing methods inadvertently modify non-target regions, particularly neighboring text. Through systematic evaluation on 50 real-world scenes across four categories, we reveal that state-of-the-art diffusion editing models exhibit a spillover rate of 94%, meaning nearly all non-target text regions are altered during editing. To address this, we propose the Edit Fidelity Field (EFF), a semantics-aware continuous field that controls per-pixel editing fidelity. Unlike binary masks, EFF leverages OCR-detected text regions to construct a four-zone field: Edit Core (fully editable), Transition Zone (smooth decay), Protected Zone (non-target text, explicitly locked), and Background (strictly preserved). EFF operates as a training-free, model-agnostic post-processing module applicable to any diffusion-based STE method. We further propose per-region spillover quantification, a novel evaluation protocol that measures edit leakage at each non-target text region individually. Experiments demonstrate that EFF reduces spillover rate from 94% to 25% while improving non-target region preservation by +91.4 dB PSNR.