Regional Attention For Shadow Removal

Hengxing Liu, Mingjia Li, Xiaojie Guo

Abstract: Shadow, as a natural consequence of light interacting with objects, plays a crucial role in shaping the aesthetics of an image, which however also impairs the content visibility and overall visual quality. Recent shadow removal approaches employ the mechanism of attention, due to its effectiveness, as a key component. However, they often suffer from two issues including large model size and high computational complexity for practical use. To address these shortcomings, this work devises a lightweight yet accurate shadow removal framework. First, we analyze the characteristics of the shadow removal task to seek the key information required for reconstructing shadow regions and designing a novel regional attention mechanism to effectively capture such information. Then, we customize a Regional Attention Shadow Removal Model (RASM, in short), which leverages non-shadow areas to assist in restoring shadow ones. Unlike existing attention-based models, our regional attention strategy allows each shadow region to interact more rationally with its surrounding non-shadow areas, for seeking the regional contextual correlation between shadow and non-shadow areas. Extensive experiments are conducted to demonstrate that our proposed method delivers superior performance over other state-of-the-art models in terms of accuracy and efficiency, making it appealing for practical applications. Our code will be made publicly available.

Primary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: This work proposed a novel shadow removal method that achieves state-of-the-art performance while being fast and lightweight. This work makes the shadow removal process more viable for real-time or on-device applications, such as mobile photography, video production, and real-time multimedia applications. This efficiency is crucial for deploying advanced image processing capabilities in consumer technology and embedded systems. By demonstrating superior performance over existing state-of-the-art models, this approach not only sets a new benchmark for shadow removal tasks but also provides a foundation for future research in image processing and other areas of multimedia processing. Moreover, the code and demo of our method will be shared with the community after the double-blind review.

Submission Number: 2682