WavShadow: Wavelet Based Shadow Segmentation and Removal
This work addresses shadow removal in complex real-world scenarios for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles shadow removal and segmentation in computer vision by enhancing the ShadowFormer model with MAE priors, Fast Fourier Convolution blocks, and Haar wavelet features, achieving state-of-the-art results on the DESOBA dataset with improved convergence speed and quality.
Shadow removal and segmentation remain challenging tasks in computer vision, particularly in complex real world scenarios. This study presents a novel approach that enhances the ShadowFormer model by incorporating Masked Autoencoder (MAE) priors and Fast Fourier Convolution (FFC) blocks, leading to significantly faster convergence and improved performance. We introduce key innovations: (1) integration of MAE priors trained on Places2 dataset for better context understanding, (2) adoption of Haar wavelet features for enhanced edge detection and multiscale analysis, and (3) implementation of a modified SAM Adapter for robust shadow segmentation. Extensive experiments on the challenging DESOBA dataset demonstrate that our approach achieves state of the art results, with notable improvements in both convergence speed and shadow removal quality.