cs.CVNov 13, 2026

HarmonyText: Harmonious Scene Text Editing via Reverse-to-Refined Pair Synthesis and Region-Decoupled Frequency Learning

Authors: Ziqi Yi, Huiguo He, Guitao Xu, Peirong Zhang, Cheng Da, Xinyao Yu, Zhanpeng Wang, Changqian Yu, 

Organizations: South China University of Technology, Guangzhou, China · Kolors Team, KlingAI Research, Beijing, China

Abstract

Natural language-guided, mask-free scene text editing aims to modify text in real-world images using only textual instructions, yet remains challenged by unreliable pseudo-GT supervision, over-smoothed text generation, and the absence of GT-free evaluation. Existing methods often rely on imperfect pseudo-targets with background discrepancies, while standard MSE-based velocity regression tends to suppress high-frequency details, leading to blurred text boundaries and weakened local textures. To address these issues, we propose HarmonyText, a mask-free scene text editing framework with region- and frequency-aware supervision. HarmonyText introduces Region-Decoupling Optimization (RDO), which aligns edited text regions with pseudo-targets while anchoring preserved regions to the source image, and Cascaded High-Frequency Texture Guidance (CHFTG), which applies cascaded wavelet-domain constraints to preserve sharp boundaries and fine-grained textures of textual content. We further propose Reverse-to-Refined Pair Synthesis (RePair) to construct STE25K, a high-quality 25K paired dataset, and introduce a GT-free evaluation protocol with Color Distribution Divergence and a Harmony Assessment Model. Extensive experiments show that HarmonyText outperforms existing methods in text editing accuracy, background fidelity, color consistency, and perceptual harmony.

Figures & tables

Explore similar work

CardsList
  1. Towards Training-Free Scene Text Editing

    Mar 25, 2026Yubo Li, Xugong Qin, Peng Zhang +3scene text editingTraining-Free Image Editing

  2. TextSculptor: Training and Benchmarking Scene Text Editing

    May 20, 2026Yiheng Lin, Siyu Jiao, Xiaohan Lan +12Synthetic Data AugmentationText-Guided Image Editing

  3. TextWand: A Unified Framework for Scene Text Editing

    Jun 4, 2026Shuyu Wang, Zhile Guan, Hongxiu Chen +5Text-Guided Image Editingscene text editing