WeEdit：一个数据集、基准和基于字形引导的文本中心图像编辑框架
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
AI总结：
WeEdit通过构建大规模数据集和定制训练策略，提升文本中心图像编辑的精度与多样性，优于现有开源模型。
摘要：
基于指令的图像编辑旨在根据用户提供的指令修改现有图像中的特定内容，同时保持非目标区域。除了传统的对象和风格中心操作外，文本中心图像编辑专注于修改、翻译或重新排列图像中的文本元素。然而，现有领先的模型往往难以精确执行复杂的文本编辑，经常产生模糊或幻觉的字符。我们将这些失败主要归因于缺乏专门针对文本中心编辑的训练范式，以及缺乏大规模数据集和标准化基准，这些是闭环训练和评估系统所必需的。为了解决这些限制，我们提出了WeEdit，一个系统性的解决方案，包括可扩展的数据构建管道、两个基准和定制的两阶段训练策略。具体而言，我们提出了一种基于HTML的自动编辑管道，生成涵盖多样编辑操作和15种语言的330,000对训练数据，并伴有标准化的双语和多语言基准以进行全面评估。在算法方面，我们采用字形引导的监督微调来注入显式的空间和内容先验，随后进行多目标强化学习阶段以对齐生成与指令遵循、文本清晰度和背景保存。广泛的实验表明，WeEdit在各种编辑操作上都显著优于先前的开源模型。
英文摘要：
Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond traditional object- and style-centric manipulation, text-centric image editing focuses on modifying, translating, or rearranging textual elements embedded within images. However, existing leading models often struggle to execute complex text editing precisely, frequently producing blurry or hallucinated characters. We attribute these failures primarily to the lack of specialized training paradigms tailored for text-centric editing, as well as the absence of large-scale datasets and standardized benchmarks necessary for a closed-loop training and evaluation system. To address these limitations, we present WeEdit, a systematic solution encompassing a scalable data construction pipeline, two benchmarks, and a tailored two-stage training strategy. Specifically, we propose a novel HTML-based automatic editing pipeline, which generates 330K training pairs covering diverse editing operations and 15 languages, accompanied by standardized bilingual and multilingual benchmarks for comprehensive evaluation. On the algorithmic side, we employ glyph-guided supervised fine-tuning to inject explicit spatial and content priors, followed by a multi-objective reinforcement learning stage to align generation with instruction adherence, text clarity, and background preservation. Extensive experiments demonstrate that WeEdit outperforms previous open-source models by a clear margin across diverse editing operations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
