FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors
This work addresses shadow removal in computer vision, which is important for applications like image editing and autonomous systems, but it appears incremental as it builds on existing unsupervised methods with specific improvements.
The paper tackles the problem of unsupervised shadow removal by proposing FASR-Net, which leverages frequency priors and novel modules to enhance shadow details, achieving superior performance on AISTD and SRD datasets.
Shadow removal is challenging due to the complex interaction of geometry, lighting, and environmental factors. Existing unsupervised methods often overlook shadow-specific priors, leading to incomplete shadow recovery. To address this issue, we propose a novel unsupervised Frequency Aware Shadow Removal Network (FASR-Net), which leverages the inherent frequency characteristics of shadow regions. Specifically, the proposed Wavelet Attention Downsampling Module (WADM) integrates wavelet-based image decomposition and deformable attention, effectively breaking down the image into frequency components to enhance shadow details within specific frequency bands. We also introduce several new loss functions for precise shadow-free image reproduction: a frequency loss to capture image component details, a brightness-chromaticity loss that references the chromaticity of shadow-free regions, and an alignment loss to ensure smooth transitions between shadowed and shadow-free regions. Experimental results on the AISTD and SRD datasets demonstrate that our method achieves superior shadow removal performance.