Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing

arXiv:2405.04377v1 Announce Type: new
Abstract: Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly coupled features for all tasks, resulting in sub-optimal performance. We propose a Disentangled Representation Learning framework (DARLING) aimed at disentangling these two types of features for improved adaptability in better addressing various downstream tasks (choose what you really need). Specifically, we synthesize a dataset of …

abstract arxiv cs.cv editing features images information performance recognition representation representation learning style tasks text texture type