DocShaDiffusion: Diffusion Model in Latent Space for Document Image Shadow Removal

TL;DR

DocShaDiffusion introduces a novel latent space diffusion model with shadow-specific modules for effective removal of both color and non-color shadows in document images, outperforming existing methods.

Contribution

The paper presents a new diffusion model in latent space for document shadow removal, including modules for shadow mask generation and noise addition, addressing color shadow challenges.

Findings

Outperforms state-of-the-art methods on three datasets.

Effectively removes color and non-color shadows.

Provides a large-scale synthetic dataset for training.

Abstract

Document shadow removal is a crucial task in the field of document image enhancement. However, existing methods tend to remove shadows with constant color background and ignore color shadows. In this paper, we first design a diffusion model in latent space for document image shadow removal, called DocShaDiffusion. It translates shadow images from pixel space to latent space, enabling the model to more easily capture essential features. To address the issue of color shadows, we design a shadow soft-mask generation module (SSGM). It is able to produce accurate shadow mask and add noise into shadow regions specially. Guided by the shadow mask, a shadow mask-aware guided diffusion module (SMGDM) is proposed to remove shadows from document images by supervising the diffusion and denoising process. We also propose a shadow-robust perceptual feature loss to preserve details and structures in document images. Moreover, we develop a large-scale synthetic document color shadow removal dataset (SDCSRD). It simulates the distribution of realistic color shadows and provides powerful supports for the training of models. Experiments on three public datasets validate the proposed method's superiority over state-of-the-art. Our code and dataset will be publicly available.