Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context

TL;DR

This paper introduces CTRNet, a novel neural network that effectively restores complex backgrounds in text removal tasks by modeling local and global context, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a new Contextual-guided Text Removal Network with a Local-global Content Modeling block combining CNNs and Transformers for improved background recovery.

Findings

CTRNet outperforms state-of-the-art methods on benchmark datasets.

The LGCM block effectively captures local and global features.

The method demonstrates strong generalization on examination papers.

Abstract

Text removal has attracted increasingly attention due to its various applications on privacy protection, document restoration, and text editing. It has shown significant progress with deep neural network. However, most of the existing methods often generate inconsistent results for complex background. To address this issue, we propose a Contextual-guided Text Removal Network, termed as CTRNet. CTRNet explores both low-level structure and high-level discriminative context feature as prior knowledge to guide the process of background restoration. We further propose a Local-global Content Modeling (LGCM) block with CNNs and Transformer-Encoder to capture local features and establish the long-term relationship among pixels globally. Finally, we incorporate LGCM with context guidance for feature modeling and decoding. Experiments on benchmark datasets, SCUT-EnsText and SCUT-Syn show that CTRNet significantly outperforms the existing state-of-the-art methods. Furthermore, a qualitative experiment on examination papers also demonstrates the generalization ability of our method. The codes and supplement materials are available at https://github.com/lcy0604/CTRNet.