scene text recognition (STR) has been extensively studied in last few years.
Many recently-proposed methods are specially designed to accommodate the
arbitrary shape, layout and orientation of scene texts, but ignoring that
various font (or writing) styles also pose severe challenges t
本文提出了一种名为 FAST 的新颖无字体场景文本编辑框架,用于在保留自然和逼真外观的同时,同时在任意样式和位置生成文本,通过结合遮罩生成和样式转移。通过滤波机制去除背景干扰,使网络仅集中于需要编辑的文本区域,同时设计了文本样式转移模块以减轻不同字长度带来的挑战,实验证明该方法在质量和数量上优于现有方法。