Recent deep learning methods have achieved promising results in image shadow removal. However, most of the existing approaches focus on working locally within shadow and non-shadow regions, resulting in severe artifacts around the shadow boundaries as well as inconsistent illumination between shadow and non-shadow regions. It is still challenging for the deep shadow removal model to exploit the global contextual correlation between shadow and non-shadow regions. In this work, we first propose a Retinex-based shadow model, from which we derive a novel transformer-based network, dubbed ShandowFormer, to exploit non-shadow regions to help shadow region restoration. A multi-scale channel attention framework is employed to hierarchically capture the global information. Based on that, we propose a Shadow-Interaction Module (SIM) with Shadow-Interaction Attention (SIA) in the bottleneck stage to effectively model the context correlation between shadow and non-shadow regions. We conduct extensive experiments on three popular public datasets, including ISTD, ISTD+, and SRD, to evaluate the proposed method. Our method achieves state-of-the-art performance by using up to 150X fewer model parameters.

翻译：近年来，深度学习方法在图像阴影去除任务中取得了令人瞩目的成果。然而，现有的大多数方法仅局限于在阴影区域和非阴影区域内进行局部处理，导致阴影边界处出现严重伪影，且阴影区域与非阴影区域之间的光照不一致。深度阴影去除模型仍难以有效利用阴影区域与非阴影区域之间的全局上下文关联。本文首先提出一种基于Retinex理论的阴影模型，并据此推导出一种新型基于Transformer的网络架构（命名为ShadowFormer），旨在利用非阴影区域辅助阴影区域恢复。我们采用多尺度通道注意力框架以分层方式捕获全局信息。在此基础上，在瓶颈阶段提出具有阴影交互注意力（SIA）的阴影交互模块（SIM），以高效建模阴影区域与非阴影区域之间的上下文关联。在ISTD、ISTD+和SRD三个公开数据集上进行了广泛实验以评估所提方法。我们的方法在使用最多比现有模型少150倍的参数量的情况下，取得了最先进的性能表现。