“…Optical Character Recognition (OCR) is an important task that has been studied in academia for a long period [85,7]. It has undergone remarkable development in the last decade, contributing to many applications like autonomous driving [87,71], car license plate recognition [99,51], GPT models [74,28], etc. Various datasets [31,19,88,89] and downstream tasks are included within this field, such as text image recognition [75,39,93,14], detection [104,49,40,82], segmentation [88,89,105,66], super-resolution [9,83,48,102], as well as some generation tasks, including text image editing [86,76,92,57,36], document layout generation [54,22,20,38,32], font generation [30,21,35,52], etc.…”