DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal

TL;DR

This paper introduces DocDeshadower, a frequency-aware Transformer model that effectively removes shadows from scanned documents by decomposing images into multiple frequency bands and employing specialized modules for different scales.

Contribution

The paper presents a novel multi-frequency Transformer architecture based on the Laplacian Pyramid for improved document shadow removal, addressing limitations of existing methods.

Findings

Outperforms state-of-the-art shadow removal methods

Effectively handles varying shadow intensities and scales

Preserves document details while removing shadows

Abstract

Shadows in scanned documents pose significant challenges for document analysis and recognition tasks due to their negative impact on visual quality and readability. Current shadow removal techniques, including traditional methods and deep learning approaches, face limitations in handling varying shadow intensities and preserving document details. To address these issues, we propose DocDeshadower, a novel multi-frequency Transformer-based model built upon the Laplacian Pyramid. By decomposing the shadow image into multiple frequency bands and employing two critical modules: the Attention-Aggregation Network for low-frequency shadow removal and the Gated Multi-scale Fusion Transformer for global refinement. DocDeshadower effectively removes shadows at different scales while preserving document content. Extensive experiments demonstrate DocDeshadower's superior performance compared to state-of-the-art methods, highlighting its potential to significantly improve document shadow removal techniques. The code is available at https://github.com/leiyingtie/DocDeshadower.